CHAT Docs

Streamline your scheduling process and eliminate the endless back-and-forth of email coordination with our advanced AI Agent and Chatbot Booking System. By integrating powerful tools like TidyCal, Calendly, and Google Calendar directly into your chat widget, you allow leads and customers to book appointments effortlessly 24/7. This automated system is not just a convenience; it is a scalable solution ideal for doctors managing patient intake, online course providers scheduling student 1:1s, and consultants securing high-value meetings.

Automated Appointment & Booking System Overview

Transform your chat widget into a fully functional scheduling assistant. Whether you are using TidyCal for cost-effective scheduling, Calendly for professional meeting coordination, or Google Calendar for direct time-blocking, the AI chatbot acts as your personal secretary. It can check availability, book slots, and manage cancellations in real-time.

TidyCal Integration

TidyCal is a favorite among freelancers and small business owners for its simplicity. Enable this integration to authorize the OpenAI chatbot to access your TidyCal account directly. This allows users to book appointments and manage them seamlessly within your existing TidyCal ecosystem.

AI Tasks for TidyCal

• Book an event: The chatbot can book events in your TidyCal on behalf of the user, automating the intake process.
• Update an event: The chatbot allows users to reschedule by updating an existing event in your TidyCal account.
• Cancel an event: If plans change, the chatbot can cancel an existing event for a user instantly.
• List events: The chatbot can retrieve and list all upcoming events associated with a specific user.
• Show available booking times: The chatbot checks your calendar in real-time to show only the available booking times to the visitor.

TidyCal Setup Guide

Calendly Booking Workflow

With the Calendly integration, scheduling meetings with your site visitors becomes a breeze. Your leads can easily book appointments directly from the chat widget. Follow these steps to send a Calendly booking invitation via the chat.

1. Create an event type from https://calendly.com/event_types/user/me.
2. Click Share and copy the URL.
3. To send the invitation, utilize the rich message button type.

Ensure you enter the Calendly URL you copied in the previous step as the URL. Additionally, include the success attribute to customize the confirmation message that will be sent to the user after the booking is successfully completed.

[button link="https://calendly.com/your-name/meeting" name="Schedule a meeting" success="Thank you! Your meeting has been scheduled."]

Google Calendar Automation

Enable this integration to allow the OpenAI chatbot to directly access your Google Calendar. This integration is powerful for service businesses requiring strict time management, allowing users to book appointments and manage them in real-time on your calendar.

AI Tasks for Google Calendar

• Book an event: The chatbot can book events in your Google Calendar on behalf of the user.
• Update an event: Users can request changes, and the chatbot can update an existing event directly in your calendar.
• Cancel an event: The chatbot can cancel an existing event for a user if necessary.
• List events: The chatbot can list the events of a user from your Google Calendar to confirm schedules.
• Show available booking times: The chatbot proactively shows available booking times to avoid scheduling conflicts.

Google Calendar Setup

Setting up Google Calendar requires a few simple synchronization steps.

1. Go to Settings > Artificial Intelligence > Google Calendar integration and click Activate.
2. Click Settings > Artificial Intelligence > Google > Synchronize and complete the synchronization process to authorize access.
3. Set the available booking times under Settings > Miscellaneous > Scheduled Office Hours.

You are done. The chatbot can now book and manage events in your Google Calendar.

Use Cases for Automated Scheduling

Automated booking systems are revolutionizing how service-based sectors operate. By removing the friction of manual scheduling, professionals can focus on delivering value rather than managing calendars.

The settings below are related to the Artificial Intelligence app.

• From Settings > Apps, click Artificial Intelligence and activate the app..

The human takeover happens in these cases:

• When a human agent replies to a user’s message.
• When the Settings > Artificial Intelligence > Human takeover > Active option is checked. It is triggered automatically when the chatbot fails to understand a user’s message or it can be requested manually by the user explicitly asking to contact a human agent.

• When the human takeover is activated the chatbot is automatically disabled for as long as the last human agent that replied to the conversation is online. If no agents have responded to the conversation yet, the chatbot will remain active. After that, the chatbot is activated again but no default fallback messages will be sent within 10 days of human takeover if the chatbot doesn’t know the answer to the user’s question in the same conversation. You can force a Dialogflow message to be always sent by adding to the Intent the custom Payload value “force-message”: true.
• The chatbot is fully activated again if the conversation is archived or deleted.
• If you’re using Slack, no messages will be sent if the chatbot knows the answer. Once the human takeover is active all conversation’s messages are sent to Slack.
• When a human agent reply to a user the human takeover is activated automatically.
• The human takeover feature is compatible with OpenAI and will continue to function even if the Dialogflow chatbot is deactivated.
• To fully disable the chatbot on human takeover, check the option Human takeover > Disable chatbot.
• If the human takeover is already active, it will not be activated again, and the human takeover message will not be sent. The fallback message will be sent instead.
• The Settings > Artificial Intelligence > Human takeover > Fallback message feature sends an automatic fallback message when a user sends a new message while human takeover is active. It’s useful for letting users know that their messages have been received and that an agent will reply shortly. The fallback message is sent at most once every 30 minutes and only if the user’s new message is sent more than 30 minutes after the last agent reply.
• Human takeover works seamlessly across all messaging apps, like WhatsApp, Messenger, Telegram, and others. Users don’t need to click a confirmation button, any text reply confirming the request will activate the human takeover automatically.

When the option Human takeover is active the following happens:

• If enabled, the request is sent only if the message sent by the user is longer than 3 chars and contains at least two words. This optimization prevents mistaken requests.
• The conversations to which the chatbot was able to answer correctly, are marked as read and moved at the bottom of the Inbox list.

When the user confirms the human takeover, or if it is automatic, the following happens:

• The conversation is marked as unread and moved on top of the Inbox.
• Any future user messages in the same conversation sent within 10 days of the human takeover will trigger agent notifications.
• If agents email notifications are active, an email notification is sent to the agent assigned to the conversation, or, if the user’s conversation is assigned to a department, to the agents assigned to that department, otherwise it is sent to all offline agents.
• If Push notifications are active, a push notification is sent to the agent assigned to the conversation, or, if the user’s conversation is assigned to a department, to the agents assigned to that department, otherwise it is sent to all offline agents.
• If text message notifications are active, a text message is sent to the agent assigned to the conversation, or, if the user’s conversation is assigned to a department, to the agents assigned to that department, otherwise it is sent to all offline agents.
• No human takeover requests within 10 days of the human takeover will be sent in the same conversation.
• The follow-up message and offline message are activated.
• If queue settings are active, the queue or routing is activated.

• You can manually trigger the human takeover by creating a new Dialogflow Intent with the following Custom Payload response: { “human-takeover”: true }.
• The manual takeover automatically notify agents via email and leave the conversation marked as unread.
• To manually send a human take over request use the chips rich message with ID sb-human-takeover. Ex. [chips id=”sb-human-takeover” options=”Human support,Cancel” message=””].

• The human takeover can be requested manually by the user explicitly asking to contact a human agent. This setting is active by default.

You can enable the human takeover for specific user messages via Q&A by adding the human takeover action in set data and actions.

To enable human takeover on an OpenAI Assistant add the following function in the OpenAI functions area:

                                {
                                    "name": "sb-human-takeover",
                                    "description": "I want to contact a human support agent or team member. I want human support.",
                                    "parameters": {
                                        "type": "object",
                                        "properties": {},
                                        "required": []
                                    }
                                }
                            

Smart Reply suggests quick responses in real-time during a conversation. Once active, you will see the suggested replies in the conversation area, if any.

• The Smart Reply feature initially checks for suggestions from the Dialogflow chatbot, provided it is active. If there is at least one suggestion, it will promptly display the results. However, if Dialogflow is inactive, or there are Dialogflow suggestions, the OpenAI suggestions will be returned instead.
• If the language detection feature is active, the smart replies will use language detection as well.
• If the multilingual via translation feature is enabled, the smart replies will utilize multilingual translation as well.
• To read the complete text of a smart reply, hover the mouse pointer over it for a duration of 3 seconds.
• To restore the previous message, press the keyboard shortcuts CTRL + Z.

CHAT.devad.io provides powerful tools to assist you in the process of creating the chatbot.

• Activate Artificial Intelligence > Google > Dialogflow chatbot. If you have general or specific inquiries that require a definitive response, or if you want to use rich messages like buttons, the Dialogflow chatbot is the best option and it can work alongside the OpenAI chatbot. The Dialogflow and OpenAI chatbots can work together simultaneously. More details here.
• Keep improviding the chatbot from the chatbot training panel.
• Activate Artificial Intelligence > Smart Reply. More details here.
• Activate the following OpenAI settings: Chatbot, Spelling Correction, Dialogflow spelling correction, Rewrite Message Button. More details here.
• Train your OpenAI chatbot with your own content, more details here.
• Set the value of Google > Dialogflow Intent detection confidence to 0.81.
• If your website receives traffic from multiple countries, consider activating the following Google options: multilingual via translation, automatic translation, language detection.
• Change the chatbot name from Settings > Users > Bot name.

The most frequent reasons for OpenAI or Google not functioning properly are listed below. For more details about the issue, open the browser developer tools and then the console tab, send a message through the CHAT.devad.io chat, and an error should appear in the console. On Chrome you can open the console from Settings > More tools > Developer tools > Console.

• There is a human takeover.
• You can hire us to make the synchronization for you, details at the hire us page.

• Click the Settings > Artificial Intelligence > OpenAI > Troubleshoot problems button and check for any error. If there is an error, it will be related to your OpenAI account, follow the error message instructions to fix the issue.
• Make sure to check the option Settings > Artificial Intelligence > OpenAI > Chatbot.
• You reached the quote limit or you are encountering billing problems with your OpenAI account. Check it at https://platform.openai.com/account/usage.
• If Dialogflow is enabled, OpenAI may not work correctly because your Dialogflow agent does not have the Fallback Intent. Please verify its presence on the Intents page, and if it’s missing, you can create it again by following the instructions here. To quickly check if this is the issue, you can disable Dialogflow and send a message consisting of 2-3 words. Then, check if the browser console has errors.
• If the chatbot is not replying at all and you have some Google setting active, try to disable the Google settings and check if the chatbot is working.
• Make sure to read the general information.
• If the training is not working as intended, for instance, if the chatbot is not responding to questions relevant to the training data, try to delete all training data from Chatbot > Training > Informaion > Delete all training data and train the chatbot again.
• If the training is not working as intended, for instance, if the chatbot replies are cut off or partially incorrect, try asking the same question a few more times. The responses should improve over time. OpenAI is needs to learn from the user interactions.
• If your training data is from a website, and the website is multilingual, make sure the lang attribute of the <html> tag contains the correct language.
• Delete all of your OpenAI settings, leave only the OpenAI key and try again.
• Try to use the OpenAI assistant instead.
• If you are having issue with ai answers, you can use our OpenAI key by setting Settings > Artificial Intelligence > OpenAI > Sync mode to Automatic. If this resolves your problems, it means that the issue originates from your OpenAI account. You need to purchase credits to use this option.
  

Here are the top 10 common issues your end users might face with the OpenAI:

API Key Invalid or Expired
Users may encounter errors if their OpenAI API key is invalid, missing, or expired.

Rate Limiting or Quota Exceeded
Requests may be throttled or rejected if users exceed their allotted usage limits or request rate.

Latency or Slow Response Times
Users might experience delays in receiving responses from the OpenAI API due to network or server load.

Unexpected or Incorrect AI Outputs
The AI may generate inaccurate, irrelevant, or misleading content, sometimes called hallucinations. We highly Recommand you using default settings, if it failed use our Ai credit or try OpenAI Assistant API for better results

Authentication Failures
Failures in authenticating API requests due to improper key usage or configuration issues.

Usage Costs and Billing Concerns
Users may face unexpected charges or misunderstandings about billing tied to their consumption of the OpenAI service.

Integration or Compatibility Issues
Challenges integrating OpenAI API into user applications, including SDK version mismatches or unsupported platforms.

Security and Data Privacy Questions
Concerns regarding how user data and queries are handled, stored, or protected by OpenAI.

Limited Feature Access or Model Availability
Access restrictions to certain models or features based on plan limits or regional availability.

• Click the Settings > Artificial Intelligence > Google > Troubleshoot problems button and check for any error. If there is an error, it will be related to your Google account, follow the error message instructions to fix the issue.
• Make sure to check the option Settings > Artificial Intelligence > Google > Dialogflow chatbot.
• If your synchronization was not successful we suggest reviewing our documentation and repeating the synchronization steps to correct any errors. If needed, we provide integration services. Details at the hire us page.
• You selected the wrong agent location.
• Make sure are not using a mega agent.
• Make sure to read the general information.

Artificial Intelligence Module Installation

To unlock the power of automated support, navigate to Settings > Apps, select Artificial Intelligence, and enter your license key to install and activate the application. If you are utilizing the cloud version of our platform, simply click Active to begin.

Human Takeover System

The Human Takeover system ensures a seamless transition between your AI chatbot and human support agents. It is designed to prioritize human interaction whenever necessary, preventing the chatbot from interfering during a live conversation.

Triggers & Activation

• Agent Reply: Takeover activates instantly when a human agent sends a message.
• Automatic: Triggered when the chatbot fails to understand a user query (if enabled in settings).
• Manual Request: Users can explicitly ask to speak to a human. This works seamlessly across WhatsApp, Telegram, and other channels without needing clickable buttons.

Optimized Requests: To prevent accidental triggers, automatic requests are only sent if the user’s message exceeds 3 characters and contains at least two words.

OpenAI Integration & Configuration

Integrating OpenAI (ChatGPT) gives your chatbot the ability to understand natural language and answer questions based on your specific data sources.

Chatbot Response Modes

• General Questions: The bot uses its general knowledge to answer. It ignores your specific training data.
• Sources Only: The bot only answers based on the data you have provided (PDFs, website, etc.). It strictly ignores general knowledge questions.
• All Questions (Recommended): The bot prioritizes your specific data but falls back to general knowledge for other inquiries.
• Assistant: Select this if you are connecting a custom OpenAI Assistant created in the OpenAI dashboard.

OpenAI Assistants

You can link your own Assistants created at platform.openai.com/assistants. To use multiple assistants, link their IDs to specific departments in Settings > Artificial Intelligence > OpenAI Assistants – Department linking. Note: Assistants are used for chat responses and smart replies, but not for features like message rewriting.

Training Your Chatbot

Training allows the AI to learn from your specific business content. You can train the bot using various sources found under the Chatbot > Training menu.

Google Calendar Integration

Allow the chatbot to book, update, and cancel appointments directly on your Google Calendar. Enable this via Settings > Artificial Intelligence > Google Calendar integration.

Multilingual Capabilities

The AI module supports advanced multilingual features to serve a global audience.

• Automatic Translation: Real-time translation of user messages into the agent’s language and vice-versa. Requires configuring the Cloud Translation API.
• Multilingual via Translation: Automatically translates static text (rich messages, articles, forms) into the user’s language. This is cost-effective as it caches translations.
• Language Detection: Automatically detects the user’s language from their first few messages (minimum 2 words) and switches the chat language context accordingly.

Advanced AI Features

Smart Reply: Suggests quick responses to agents in real-time. It prioritizes data from Dialogflow (if active) and then falls back to OpenAI suggestions.
Message Rewriting: Agents can click a button to rewrite their draft message to be more friendly and professional.
Speech & Image Recognition: The bot can convert audio messages to text and analyze images sent by users (requires GPT-4 models).

The following integrations are available from Settings > Artificial Intelligence and can be used to enhance the OpenAI chatbot’s capabilities Lead Generation & Customers. Integrations are conversational, multilingual, and compatible with any messaging app such as WhatsApp, Messenger, Telegram, and more.

Enable this integration to allow the OpenAI chatbot to access your Google Calendar, so users can book appointments and manage them on your calendar.

• Book an avent: The chatbot can book events in your Google Calendar on behalf of the user.
• Update an avent: The chatbot can update an existing event for a user in your Google Calendar.
• Cancel an avent: The chatbot can cancel an existing event for a user in your Google Calendar.
• List events: The chatbot can list the events of a user from your Google Calendar.
• Show available booking times: The chatbot can show the available booking times.

• Go to Settings > Artificial Intelligence > Google Calendar integration and click Activate.
• Click Settings > Artificial Intelligence > Google > Synchronize and complete the synchronization process.
• Set the available booking times under Settings > Miscellaneous > Scheduled Office Hours.
• You are done. The chatbot can now book and manage events in your Google Calendar.

• The Slot duration setting is the duration of the booked event.
• The Buffer time setting is used to add a buffer (in minutes) between bookings so you are not booked back-to-back.
• The Minimum booking time setting is the minimum time (in minutes) required to book an event from the current time. It is used to prevent bookings too close to the current time.

Enable this integration to allow the OpenAI chatbot to access your TidyCal account, so users can book appointments and manage them on your TidyCal account.

• Book an avent: The chatbot can book events in your TidyCal on behalf of the user.
• Update an avent: The chatbot can update an existing event for a user in your TidyCal.
• Cancel an avent: The chatbot can cancel an existing event for a user in your TidyCal.
• List events: The chatbot can list the events of a user from your TidyCal.
• Show available booking times: The chatbot can show the available booking times.

• Go to Settings > Artificial Intelligence > TidyCal integration and click Activate.
• In your TidyCal account, go to Integrations > Advanced > API Keys or click here. Create a Personal Access Token, copy it, and paste it into Settings > Artificial Intelligence > TidyCal integration > Access token. Then, save the changes.
• Enter the title of the booking type you want to use in Settings > Artificial Intelligence > TidyCal integration > Booking type title, and save the changes.
• Configure the available booking times, buffer times before and after bookings, and the slot duration directly in your TidyCal account.
• You are done. The chatbot can now book and manage events in your TidyCal account.

• Only events without a price are supported.
• The selected booking type is cached for 24 hours. If you update it, you may need to wait up to 24 hours for the changes to take effect. To apply changes immediately, create a new booking type or change its title and update it in the CHAT.devad.io settings.

FAQs

Q: How can I integrate Google Calendar or TidyCal with the lead management system?
You can connect your Google Calendar or TidyCal account through the integration settings in the CHAT App dashboard to sync appointments and manage leads seamlessly.

Q: Can the chatbot create, update, or cancel appointments automatically?
Yes, the chatbot can create, update, cancel, and display bookings in real time while keeping everything synchronized with Google Calendar or TidyCal.

Q: Are appointment settings like office hours and buffer times customizable?
Absolutely. You can configure available time slots, office hours, slot durations, and buffer times from the CHAT App dashboard to suit your lead management needs.

Q: How do leads book appointments through the chatbot?
Leads can book appointments naturally via a chat conversation with the AI chatbot without filling out forms; the chatbot guides them smoothly through the scheduling process.

Q: Can admins and agents manage bookings directly from the CHAT App panel?
Yes, admins and agents have real-time access to view, cancel, or create appointments via the CHAT App admin panel, with full synchronization to Google Calendar or TidyCal.

Q: Is the chatbot multilingual for booking appointments?
Yes, the integrations are fully multilingual, allowing the chatbot to understand and respond in any language, making global lead management easy.

Q: Which messaging platforms support booking through Google Calendar or TidyCal?
The booking integrations work across WhatsApp, Messenger, Telegram, Instagram, Line, Viber, Zalo, WeChat, Email, and SMS platforms.

Q: How quickly can I set up the Google Calendar or TidyCal integration?
Setting up either integration takes only a few minutes and involves connecting your account and configuring your preferences through CHAT App .

Q: Can the chatbot handle appointment reminders and notifications?
Yes, with the integrations, your AI chatbot can send booking confirmations, reminders, and updates automatically via supported messaging platforms.

Q: What should I do if appointments don’t sync correctly between CHAT App and Google Calendar or TidyCal?
Ensure your integration is properly connected and authorized in the dashboard; real-time synchronization should maintain consistency, and quick setup guides are available to troubleshoot potential syncing issues
Q: What is Lead Management in the cloud version?
Lead Management helps you organize, track, and manage potential customers’ information and interactions efficiently in one place.

Q: How can I add a new lead manually?
You can add new leads manually through the admin panel or import them using supported formats.

Q: Can I track the status of a lead throughout the sales process?
Yes, the system allows you to monitor each lead’s progress from initial contact to conversion or disqualification.

Q: Is it possible to assign leads to specific agents or team members?
Yes, lead assignment can be done automatically or manually to ensure proper follow-up by the responsible agents.

Q: How do I integrate Google Calendar for managing appointments?
You can connect your Google Calendar account within the platform to schedule and sync appointments directly.

Q: Can my customers book appointments via TidyCal?
Yes, if integrated, customers can easily book appointments through TidyCal, which sync back to your calendar system.

Q: How are appointment notifications handled?
Notifications and reminders for appointments are sent automatically to both agents and customers to reduce no-shows.

Q: Can I view all my scheduled appointments in one place?
Yes, all appointments booked via Google Calendar or TidyCal appear in your unified calendar dashboard.

Q: Is it possible to reschedule or cancel appointments?
Yes, both rescheduling and cancellations are supported via the calendar integrations, with automatic updates and notifications.

Q: Does the lead management system support follow-up reminders?
Yes, you can set automated follow-up reminders to ensure timely contact with your leads for better conversion chances.

Use Case

Q: What kinds of use cases can CHAT App handle for appointments, reservations, and meeting scheduling?
CHAT App can be used in various industries for appointments and meeting management, including doctors and healthcare providers, real estate agents, salons and spas, consultants, tutors, legal services, fitness trainers, event planners, car service centers, and hospitality businesses.

Q: How can doctors use CHAT App for appointments and meeting rescheduling?
Doctors can use CHAT App to allow patients to book consultations, schedule follow-ups, and reschedule appointments. The chat interface can integrate calendars to manage availability and send automated reminders, reducing no-shows and improving patient engagement.

Q: In real estate, how does CHAT App improve appointment and reservation management?
Real estate agents can enable clients to schedule property viewings and virtual tours through CHAT App. The system can handle rescheduling requests effortlessly and send notifications to both agents and clients, streamlining the communication process.

Q: How can salons or spas utilize CHAT App features for reservations?
Salons and spas can allow clients to book treatments or services directly through the chat. CHAT App can manage appointment slots, handle cancellations or rescheduling, and notify staff, ensuring smooth operations.

Q: What benefits does CHAT App provide consultants for meeting management?
Consultants can use CHAT App to schedule client meetings or coaching sessions, manage calendars with Google Calendar or TidyCal integrations, and offer easy rescheduling or cancellations within the chat system.

Q: How can tutors or educational services use CHAT App for appointments?
Tutors can offer students a quick way to book lessons, change times, or cancel sessions through CHAT App. Automated calendar updates and reminders help reduce scheduling conflicts and absenteeism.

Q: Can legal services use CHAT App for managing client meetings?
Yes, legal professionals can streamline appointment booking, rescheduling, and client communication with CHAT App, providing an efficient and professional experience for clients.

Q: How does CHAT App assist fitness trainers in appointment booking?
Fitness trainers can manage session bookings, cancellations, and rescheduling through the chat, integrating calendars for real-time availability and automatic reminders to clients.

Q: What use does event planners have for CHAT App in reservations?
Event planners can handle client consultations, schedule planning meetings, and manage bookings for event services, allowing easy rescheduling and cancellation through CHAT App chat.

Q: How can car service centers benefit from CHAT App for appointment management?
Car service centers can allow customers to book maintenance or repair appointments, reschedule or cancel as needed, and get automated notifications, keeping the scheduling process smooth and user-friendly.

Artificial Intelligence Module Installation

To unlock the power of automated support, navigate to Settings > Apps, select Artificial Intelligence, and enter your license key to install and activate the application. If you are utilizing the cloud version of our platform, simply click Active to begin.

Human Takeover System

The Human Takeover system ensures a seamless transition between your AI chatbot and human support agents. It is designed to prioritize human interaction whenever necessary, preventing the chatbot from interfering during a live conversation.

Triggers & Activation

• Agent Reply: Takeover activates instantly when a human agent sends a message.
• Automatic: Triggered when the chatbot fails to understand a user query (if enabled in settings).
• Manual Request: Users can explicitly ask to speak to a human. This works seamlessly across WhatsApp, Telegram, and other channels without needing clickable buttons.

Optimized Requests: To prevent accidental triggers, automatic requests are only sent if the user’s message exceeds 3 characters and contains at least two words.

OpenAI Integration & Configuration

Integrating OpenAI (ChatGPT) gives your chatbot the ability to understand natural language and answer questions based on your specific data sources.

Chatbot Response Modes

• General Questions: The bot uses its general knowledge to answer. It ignores your specific training data.
• Sources Only: The bot only answers based on the data you have provided (PDFs, website, etc.). It strictly ignores general knowledge questions.
• All Questions (Recommended): The bot prioritizes your specific data but falls back to general knowledge for other inquiries.
• Assistant: Select this if you are connecting a custom OpenAI Assistant created in the OpenAI dashboard.

OpenAI Assistants

You can link your own Assistants created at platform.openai.com/assistants. To use multiple assistants, link their IDs to specific departments in Settings > Artificial Intelligence > OpenAI Assistants – Department linking. Note: Assistants are used for chat responses and smart replies, but not for features like message rewriting.

Training Your Chatbot

Training allows the AI to learn from your specific business content. You can train the bot using various sources found under the Chatbot > Training menu.

Google Calendar Integration

Allow the chatbot to book, update, and cancel appointments directly on your Google Calendar. Enable this via Settings > Artificial Intelligence > Google Calendar integration.

Multilingual Capabilities

The AI module supports advanced multilingual features to serve a global audience.

• Automatic Translation: Real-time translation of user messages into the agent’s language and vice-versa. Requires configuring the Cloud Translation API.
• Multilingual via Translation: Automatically translates static text (rich messages, articles, forms) into the user’s language. This is cost-effective as it caches translations.
• Language Detection: Automatically detects the user’s language from their first few messages (minimum 2 words) and switches the chat language context accordingly.

Advanced AI Features

Smart Reply: Suggests quick responses to agents in real-time. It prioritizes data from Dialogflow (if active) and then falls back to OpenAI suggestions.
Message Rewriting: Agents can click a button to rewrite their draft message to be more friendly and professional.
Speech & Image Recognition: The bot can convert audio messages to text and analyze images sent by users (requires GPT-4 models).

The information below is related to the chatbot flows area. Flows allows you to esely create conversation flows powered by the chatbot. Use them to guide the user toward a specific goal with a series of pre-defined messages.

Flow blocks

• Start: Use the start block to set when the flows should start. It can be everytime the user start a new conversation, when it sends a specific message, or on page load. If you set conditions, the flow will only start when all conditions are met. If you set a depertment, the flow will only start for conversations assigned to that department. If you set a source, the flow will only start for conversations from that source.
• Send message: Send a message to the user.
• Send choices: Send a list of buttons to the user or allow it to choose one. When conversational mode is enabled, buttons are hidden, the chatbot sends only text, and users select options by replying with text. The AI interprets the message and selects the corresponding option, continuing the flow as if the button were pressed. This creates a more natural, chat-like experience and is automatically activated, only when needed, on messaging channels such as WhatsApp and Instagram. If the user’s reply doesn’t match any option, a fallback message with the available choices will be sent. You can add variations to the button texts by separating them with the | char, for example: Yes|Yeah|Sure. They will help the AI to understand the user reply.
• Send video: Send a video to the user.
• Get user details: Get the user details and store them in CHAT.devad.io. You will see such values in the user details panel. You can leave the description field empty for default details, but it’s required if using custom user fields. Note that user details will not be saved if you test this flow in the playground, as the user there is temporary. To see details saved, test the flow with a real user.
• Set data: Set the specified user values when the block is executed. You will see such values in the user details panel.
• Actions: Execute the specified actions when the block is executed.
• Conditions: Use it to create different branches in the flow. If the conditions are met, the flow will follow the branch set as true, otherwise the one set as false.
• Rest API: Use it to send data to your server. The body must be a JSON array. Details like user ID and conversation ID are automatically included in the data sent to your server under the sb key. Use the save response section to save specified user details with values from your server response. Use the JSON dot notation. Our support doesn’t include assistance with this feature, as it is for advanced users and requires custom code on your server. For help with this, feel free to hire us.
• Tools calling: For more details go here.
• Flow connector: Connect the flow to another flow and start it.

• Flows can be multilingual. Add translations for messages, button texts, and other content in the translations area. You can also use the multilingual via translation feature for automatic translations. If the default language of your flows is not English you have also to set the default language under Settings > Artificial Intelligence > OpenAI > Training Sources Language.
• Users can move back to earlier steps and update previously entered details in a conversational manner. For example, they might say “Sorry, I entered the wrong email”, “I need to update my email and phone number”, or even a general message like “Sorry, I entered the wrong details, go back”, which will return them to the previous step.

Q: What are Flows Builder?
Flows are sequences of interactions between the user and the chatbot that guide the user through a series of questions and answers.

Q: How can I start a Flow?
Use the Start block to set when the Flows should start, such as when a user starts a new conversation, sends a specific message, or on page load. Flows can start only when all set conditions are met.

Q: What action blocks are available in Flows?
Available blocks include Send message, Send button list, Send video, Get user details, Set data, Actions, Conditions, and Rest API.

Q: How do Conditions work in Flows?
Conditions create different branches in the Flow. If a condition is met, the Flow follows the true branch; otherwise, it follows the false branch.

Q: Can Flows collect user information?
Yes, using the Get user details block, Flows can gather and store user information.

Q: How can I send data to my server from a Flow?
Use the Rest API block to send data via a JSON array to your server. User details are included automatically under the sb key.

Q: Are there predefined Flows?
Yes, CHAT App automatically generates flows such as Registration and Follow-up flows based on specific settings.

Q: Can I customize Flows according to my needs?
Yes, you can create custom Flows combining various blocks and conditions to guide your users toward specific goals.

Q: Is technical knowledge required to use the Rest API block in Flows?
Yes, the Rest API block requires advanced knowledge and custom server code for proper integration.

Q: Can users take control from an automated Flow and talk to a human agent?
Yes, Flows support a human takeover feature where users can switch from the automated flow to live human support.

Q: How do I track the performance of my Flows?
You can monitor Flow engagement and conversion statistics in the analytics section of CHAT App to optimize your setup.

Tools calling allows to connect the chatbot to external tools and systems to retrive information needed to answer the user. The chatbot will query your server and return the information from your server to the user. The data sent to your server is in the body and it includes the user input, user ID, and conversation ID. Tools calling is used by Q&A and Flows. More details here. Our support doesn’t include assistance with this feature, as it is for advanced users and requires custom code on your server. For help with this, feel free to hire us.

• URL: Enter the URL of the API endpoint that will supply the necessary values for the function.
• Headers: If you are setting up a Q&A, enter key-value header parameters, separated by commas. E.g. apikey:123345, json:true. If you are setting up a flow, enter add key-value header parameters by clicking the Add new item button.
• Properties: Enter values that the user must provide to the chatbot. For example a city, a tracking number, etc. The chatbot will ask the user for these values. If you already know all the possible values, you can enter them in the Allowed values field.

CHAT.devad.io will send the following information to your server. If you use the POST method, it will be included in the JSON body, if you use the GET method, it will be included in the header.

{
    "sb": {
        "user_id": "123",
        "conversation_id": "123",
        "user_language": "es"
    },
    "arguments": {}
}

The arguments array contains the values provided by the user. The keys are the name converted to kebab case, for example if the property name is Order Number, the key will be order-number. The user_id is the ID of the user in CHAT.devad.io and conversation_id is the ID of the conversation. You can use these IDs to retrieve more information about the user and the conversation via the REST API.

Your server must returns a JSON array with the values required by the chatbot. Include success: true only when the request is successful and the expected information is returned. Do not include it if the information cannot be retrieved (e.g., when an invalid order number is provided). See the example below for more details.

{
    "order_status": "Delivered 2 hours and 25 minutes ago",
    "success": true
}

The settings below are related to the Artificial Intelligence app.

To start using the Google AI services and Dialogflow follow the steps below.

• Click Synchronize now and complete the procedure.
• If you want to activate the Dialogflow chatbot, check Settings > Artificial Intelligence > Google > Dialogflow chatbot. Also, you have to enter your chatbot Project ID or Agent Name, to get it follow the steps below.
• You need to purchase credits to use this option.

• Enable the CHAT.devad.io > Settings > Artificial Intelligence > Google > Dialogflow Chatbot option and save the changes.
• Go to console.cloud.google.com and sign in.
• Select or create a project by clicking the Select a project button on top-left. Name the project as you want.
• Activate the Dialogflow API by entering Dialogflow API on the top search bar. Click Dialogflow API and then click Enable. Do the same for the Cloud Natural Language API, Cloud Translation API, and Google Calendar API.
• Select the project and the go to Left menu > APIs and services > OAuth consent screen. Select External and click Create. In App name enter what you want, in User support email and Developer contact information enter your email. Click Save and continue.
• In the Data access area, click Add or remove scopes, scroll bottom and into the Manually add scopes area enter https://www.googleapis.com/auth/dialogflow,https://www.googleapis.com/auth/cloud-language,https://www.googleapis.com/auth/cloud-translation,https://www.googleapis.com/auth/calendar. Click Add to table and then Update and Save and continue.
• In the Audience area, click Add users and add your Google email, use the same email as the currently logged in account. Click Save and continue. Click PUBLISH APP. There is no need to complete the review process, leave it in the pending review state.
• Go to Left menu > APIs and services > Credentials and click Create credentials, select OAuth client ID. As Application type select Web application. Enter any name you want. In Authorised redirect URI enter the redirect URL, get it from CHAT.devad.io > Settings > Artificial Intelligence > Google > Authorised redirect URI. Click Create.
• Copy Client ID and Client Secret and paste them into CHAT.devad.io > Settings > Artificial Intelligence > Dialogflow. Save the settings.
• Click CHAT.devad.io > Settings > Artificial Intelligence > Google > Synchronize. Login with the same Google account you have used till now. On the next screen click Continue. On the next screen select all scopes and click Continue.
• Copy the Refresh token and paste it into CHAT.devad.io > Settings > Artificial Intelligence > Google > Refresh token.
• You are done! If you want to activate the Dialogflow chatbot, check Settings > Artificial Intelligence > Google > Dialogflow chatbot. Also, you have to enter your chatbot Project ID or Agent Name, to get it follow the steps below. Note that the app does not need to be approved by Google.
• If you are a Google Workspace user, go to https://admin.google.com/ and click Google Cloud Session control. Set Re-authentication policy to Never require re-authentication.

The feature Artificial Intelligence > Google > Multilingual checks if there is a Dialogflow agent in the user’s language and activate it.

• For this feature to work the user language must be know. The user language is based on the language user detail of the user if set, otherwise on the user browser language. The language can also be detected with the language detection feature.

The automatic translation feature automatically translates user messages into agent language and agent messages into user language. To enable it check the option Settings > Artificial Intelligence > Automatic translation. If you are using the cloud version and Artificial Intelligence > Google > Sync mode is set to Automatic, the multilingual features will work automatically. Otherwise you have to complete the synchronization and the setup below. The multilingual via translation and language detection features also require these steps.

• Log in to https://console.cloud.google.com with your Google account and select the project of your Dialogflow Agent.
• On the top search bar type cloud translation, select the Cloud Translation API service and enable it. Please note that this is a paid service with a free tier, additional charges may occur.
• Enable the billing by clicking Left menu > Billing and by enabling a billing account with a valid payment method.

• The user messages in the admin area are translated automatically in real-time to match the agent language.
• The agent messages are translated automatically in real-time to match the user language.
• Agents can view the original message by opening the message menu and by clicking View original message.
• The agent language is based on the language user detail of the agent if set, otherwise on the browser language, or admin area language.
• The user language is based on the language user detail, if set, otherwise on chat language, if set, otherwise on the browser language. The language can also be detected with the language detection feature.
• The notifications are also translated.
• To avoid translating a string, enclose it with the characters ` or “`.

The feature at Settings > Artificial Intelligence > Multilingual via translation automatically translates user messages into the default language of Dialogflow or OpenAI, and translates Dialogflow or OpenAI messages into the language spoken by the user. Additionally, this feature translates all text displayed within the chat, such as the chatbot’s rich messages, articles, registration forms, and pop-up notifications. To enhance performance and minimize translation costs, the translations are automatically integrated into the translation files. Combine this feature with the language detection feature for optimal results.

• If English is one of the languages, English must be the default language, the original texts must be in English.
• If you are using OpenAI with training data, set the default training data language under Settings > Artificial Intelligence > OpenAI > Training Sources Language. Leave it as default if the training data default language is in English.

Detect the language of the user’ messages and change the user language and Dialogflow agent language accordingly, if available, otherwise, show a fallback message. You can use the following merge fields in the message: {language_name}.

• The user message must be at least 2 words long.
• Language detection is executed only for the first 2 user messages of a conversation.
• As long as the OpenAI chatbot is operational and programmed to respond to generic inquiries, the fallback message will never be dispatched, since OpenAI will consistently provide answers to any use message.

The Google search feature at Settings > Artificial Intelligence > Google search gives your chatbot the ability to search for answers on Google. This feature is helpful for providing answers to questions that require real-time information.

• Register at https://programmablesearchengine.google.com/.
• Create a search and setup it is as you want. We recommend to add only your website and Wikipedia if you want your chatbot to reply to general questions, leave disabled the option Search the entire web. Use the Entities option to exclude invalid results.
• Go to Edit search engine > Setup > Basic and copy the Search engine ID value, paste it in CHAT.devad.io.
• To get the API key visit https://developers.google.com/custom-search/v1/overview and click Get a key.

In the case where Dialogflow is unable to find the appropriate response to the user’s message, this function verifies if there are any spelling errors. If any such errors exist, Dialogflow is prompted again with the correctly spelled version of the message for an accurate response. Although it has a lower priority, this feature can still work together with the OpenAI Dialogflow spelling correction feature.

The Entities setting analyze the user’s message and recognize and extract entities like cities, events, dates, and more. Use it to exclude invalid results returned by Google search. To enable this setting follow the steps below.

• Log in to https://console.cloud.google.com with your Google account and select the project of your Dialogflow Agent.
• Enter Cloud Natural Language API in the search bar at the top, select Cloud Natural Language API and enable the API .
• Enable the billing by clicking Left menu > Billing and by enabling a billing account with a valid payment method. Enable billing for the project of your Dialogflow agent.

• The Google search is performed only if the chatbot does not know the answer to the user’s question and if the length of the user’s message is greater than 4 characters.
• If the Google search returns a result, the Dialogflow context google-search is automatically activated. The context contains the attribute link which is the website’s link of the Google search result. Use the context to create a new intent that provides the link, if the user sends a message like tell me more or I want to know more.
• Google search is not required to activate the spelling correction. You can disable Google search and activate only spelling correction.
• Google search is compatible with the OpenAI chatbot.

🛠️ Google Calendar & AI Integration FAQ

Connectivity & Syncing

Q: Why is my Google Calendar not syncing with CHAT App (CHAT.devad.io)? Ensure your Google account authorization is active and has the correct permissions. This issue can also stem from incorrect OAuth credentials, expired tokens, or insufficient permissions granted during the initial setup. Check your connection and reauthorize if necessary.

Q: Why do my appointments not appear correctly in Google Calendar? This is often caused by time zone mismatches or selecting the wrong calendar in the CHAT App (CHAT.devad.io) settings. Verify that your dashboard settings match your preferred local time zone and specific calendar ID.

Q: Can I create appointments in CHAT App (CHAT.devad.io) that automatically show in Google Calendar? Yes. The platform integrates directly with Google Calendar to create, display, and update appointments automatically the moment they are scheduled via the chat interface.

Q: Why do Google contacts or calendar events sometimes not update immediately? Sync delays can occur due to API rate limits or temporary network fluctuations. Performing a manual sync or refreshing the dashboard usually resolves this.

AI & Automation Features

Q: Why am I not receiving AI-generated appointment reminders? Check your notification settings within CHAT App (CHAT.devad.io). Ensure that email or SMS reminders are enabled and that the lead’s contact details are correctly formatted.

Q: How does CHAT App (CHAT.devad.io) handle appointment rescheduling? Users can reschedule appointments naturally via chat. The system automatically updates the linked Google Calendar and sends out notifications to all involved parties to keep everyone aligned.

Q: Can AI features suggest optimal appointment times? Yes. The AI analyzes your real-time availability and recommends specific meeting times to the user, significantly improving scheduling efficiency and reducing back-and-forth messaging.

Q: How do AI features like Smart Reply or Human Takeover work? Smart Reply provides AI-powered suggested responses for quick interactions, while Human Takeover allows a seamless transition from the bot to a human agent for complex queries that require a personal touch.

Q: What should I do if the AI-generated answers are inaccurate or irrelevant? Adjust your programmable search engine setup within the app. Ensure you include only trusted domains (like your official website) and use Entity filters to exclude invalid or off-topic results.

Technical Troubleshooting & API

Q: How can I fix OAuth consent screen errors during setup? Ensure all required scopes (such as Dialogflow, Cloud Language, and Cloud Translation) are added. The OAuth consent screen must be published in the Google Cloud Console, even if it is still in the “pending review” state.

Q: What should I do if Google API requests exceed the quota limit? Review your API usage and optimize your query frequency. If your volume remains high, you can request a quota increase via the Google Cloud Console to prevent synchronization delays.

Q: What happens if the Google Workspace re-authentication policy interferes with integration? To avoid service disruptions, set the Cloud Session control’s Re-authentication policy to “Never require re-authentication” within your Google Workspace admin settings.

Privacy & Reliability

Q: Are there privacy concerns with syncing appointments? CHAT App (CHAT.devad.io) follows GDPR and global privacy laws. The system only syncs data strictly necessary for scheduling appointments and requires explicit user consent.

Q: Why am I experiencing delays in AI-generated follow-ups? Delays can stem from server loads, connectivity issues, or AI processing errors. We recommend monitoring the system status and ensuring you are using the latest version of the app for optimal performance.

The settings below are related to the Artificial Intelligence app.

• From Settings > Apps, click Artificial Intelligence and activate the app..

The human takeover happens in these cases:

• When a human agent replies to a user’s message.
• When the Settings > Artificial Intelligence > Human takeover > Active option is checked. It is triggered automatically when the chatbot fails to understand a user’s message or it can be requested manually by the user explicitly asking to contact a human agent.

• When the human takeover is activated the chatbot is automatically disabled for as long as the last human agent that replied to the conversation is online. If no agents have responded to the conversation yet, the chatbot will remain active. After that, the chatbot is activated again but no default fallback messages will be sent within 10 days of human takeover if the chatbot doesn’t know the answer to the user’s question in the same conversation. You can force a Dialogflow message to be always sent by adding to the Intent the custom Payload value “force-message”: true.
• The chatbot is fully activated again if the conversation is archived or deleted.
• If you’re using Slack, no messages will be sent if the chatbot knows the answer. Once the human takeover is active all conversation’s messages are sent to Slack.
• When a human agent reply to a user the human takeover is activated automatically.
• The human takeover feature is compatible with OpenAI and will continue to function even if the Dialogflow chatbot is deactivated.
• To fully disable the chatbot on human takeover, check the option Human takeover > Disable chatbot.
• If the human takeover is already active, it will not be activated again, and the human takeover message will not be sent. The fallback message will be sent instead.
• The Settings > Artificial Intelligence > Human takeover > Fallback message feature sends an automatic fallback message when a user sends a new message while human takeover is active. It’s useful for letting users know that their messages have been received and that an agent will reply shortly. The fallback message is sent at most once every 30 minutes and only if the user’s new message is sent more than 30 minutes after the last agent reply.
• Human takeover works seamlessly across all messaging apps, like WhatsApp, Messenger, Telegram, and others. Users don’t need to click a confirmation button, any text reply confirming the request will activate the human takeover automatically.

When the option Human takeover is active the following happens:

• If enabled, the request is sent only if the message sent by the user is longer than 3 chars and contains at least two words. This optimization prevents mistaken requests.
• The conversations to which the chatbot was able to answer correctly, are marked as read and moved at the bottom of the Inbox list.

When the user confirms the human takeover, or if it is automatic, the following happens:

• The conversation is marked as unread and moved on top of the Inbox.
• Any future user messages in the same conversation sent within 10 days of the human takeover will trigger agent notifications.
• If agents email notifications are active, an email notification is sent to the agent assigned to the conversation, or, if the user’s conversation is assigned to a department, to the agents assigned to that department, otherwise it is sent to all offline agents.
• If Push notifications are active, a push notification is sent to the agent assigned to the conversation, or, if the user’s conversation is assigned to a department, to the agents assigned to that department, otherwise it is sent to all offline agents.
• If text message notifications are active, a text message is sent to the agent assigned to the conversation, or, if the user’s conversation is assigned to a department, to the agents assigned to that department, otherwise it is sent to all offline agents.
• No human takeover requests within 10 days of the human takeover will be sent in the same conversation.
• The follow-up message and offline message are activated.
• If queue settings are active, the queue or routing is activated.

• You can manually trigger the human takeover by creating a new Dialogflow Intent with the following Custom Payload response: { “human-takeover”: true }.
• The manual takeover automatically notify agents via email and leave the conversation marked as unread.
• To manually send a human take over request use the chips rich message with ID sb-human-takeover. Ex. [chips id=”sb-human-takeover” options=”Human support,Cancel” message=””].

• The human takeover can be requested manually by the user explicitly asking to contact a human agent. This setting is active by default.

You can enable the human takeover for specific user messages via Q&A by adding the human takeover action in set data and actions.

To enable human takeover on an OpenAI Assistant add the following function in the OpenAI functions area:

                                {
                                    "name": "sb-human-takeover",
                                    "description": "I want to contact a human support agent or team member. I want human support.",
                                    "parameters": {
                                        "type": "object",
                                        "properties": {},
                                        "required": []
                                    }
                                }
                            

Smart Reply suggests quick responses in real-time during a conversation. Once active, you will see the suggested replies in the conversation area, if any.

• The Smart Reply feature initially checks for suggestions from the Dialogflow chatbot, provided it is active. If there is at least one suggestion, it will promptly display the results. However, if Dialogflow is inactive, or there are Dialogflow suggestions, the OpenAI suggestions will be returned instead.
• If the language detection feature is active, the smart replies will use language detection as well.
• If the multilingual via translation feature is enabled, the smart replies will utilize multilingual translation as well.
• To read the complete text of a smart reply, hover the mouse pointer over it for a duration of 3 seconds.
• To restore the previous message, press the keyboard shortcuts CTRL + Z.

CHAT.devad.io provides powerful tools to assist you in the process of creating the chatbot.

• Activate Artificial Intelligence > Google > Dialogflow chatbot. If you have general or specific inquiries that require a definitive response, or if you want to use rich messages like buttons, the Dialogflow chatbot is the best option and it can work alongside the OpenAI chatbot. The Dialogflow and OpenAI chatbots can work together simultaneously. More details here.
• Keep improviding the chatbot from the chatbot training panel.
• Activate Artificial Intelligence > Smart Reply. More details here.
• Activate the following OpenAI settings: Chatbot, Spelling Correction, Dialogflow spelling correction, Rewrite Message Button. More details here.
• Train your OpenAI chatbot with your own content, more details here.
• Set the value of Google > Dialogflow Intent detection confidence to 0.81.
• If your website receives traffic from multiple countries, consider activating the following Google options: multilingual via translation, automatic translation, language detection.
• Change the chatbot name from Settings > Users > Bot name.

The most frequent reasons for OpenAI or Google not functioning properly are listed below. For more details about the issue, open the browser developer tools and then the console tab, send a message through the CHAT.devad.io chat, and an error should appear in the console. On Chrome you can open the console from Settings > More tools > Developer tools > Console.

• There is a human takeover.
• You can hire us to make the synchronization for you, details at the hire us page.

• Click the Settings > Artificial Intelligence > OpenAI > Troubleshoot problems button and check for any error. If there is an error, it will be related to your OpenAI account, follow the error message instructions to fix the issue.
• Make sure to check the option Settings > Artificial Intelligence > OpenAI > Chatbot.
• You reached the quote limit or you are encountering billing problems with your OpenAI account. Check it at https://platform.openai.com/account/usage.
• If Dialogflow is enabled, OpenAI may not work correctly because your Dialogflow agent does not have the Fallback Intent. Please verify its presence on the Intents page, and if it’s missing, you can create it again by following the instructions here. To quickly check if this is the issue, you can disable Dialogflow and send a message consisting of 2-3 words. Then, check if the browser console has errors.
• If the chatbot is not replying at all and you have some Google setting active, try to disable the Google settings and check if the chatbot is working.
• Make sure to read the general information.
• If the training is not working as intended, for instance, if the chatbot is not responding to questions relevant to the training data, try to delete all training data from Chatbot > Training > Informaion > Delete all training data and train the chatbot again.
• If the training is not working as intended, for instance, if the chatbot replies are cut off or partially incorrect, try asking the same question a few more times. The responses should improve over time. OpenAI is needs to learn from the user interactions.
• If your training data is from a website, and the website is multilingual, make sure the lang attribute of the tag contains the correct language.
• Delete all of your OpenAI settings, leave only the OpenAI key and try again.
• Try to use the OpenAI assistant instead.
• If you are having issue with ai answers, you can use our OpenAI key by setting Settings > Artificial Intelligence > OpenAI > Sync mode to Automatic. If this resolves your problems, it means that the issue originates from your OpenAI account. You need to purchase credits to use this option.
  

Here are the top 10 common issues your end users might face with the OpenAI:

API Key Invalid or Expired
Users may encounter errors if their OpenAI API key is invalid, missing, or expired.

Rate Limiting or Quota Exceeded
Requests may be throttled or rejected if users exceed their allotted usage limits or request rate.

Latency or Slow Response Times
Users might experience delays in receiving responses from the OpenAI API due to network or server load.

Unexpected or Incorrect AI Outputs
The AI may generate inaccurate, irrelevant, or misleading content, sometimes called hallucinations. We highly Recommand you using default settings, if it failed use our Ai credit or try OpenAI Assistant API for better results

Authentication Failures
Failures in authenticating API requests due to improper key usage or configuration issues.

Usage Costs and Billing Concerns
Users may face unexpected charges or misunderstandings about billing tied to their consumption of the OpenAI service.

Integration or Compatibility Issues
Challenges integrating OpenAI API into user applications, including SDK version mismatches or unsupported platforms.

Security and Data Privacy Questions
Concerns regarding how user data and queries are handled, stored, or protected by OpenAI.

Limited Feature Access or Model Availability
Access restrictions to certain models or features based on plan limits or regional availability.

• Click the Settings > Artificial Intelligence > Google > Troubleshoot problems button and check for any error. If there is an error, it will be related to your Google account, follow the error message instructions to fix the issue.
• Make sure to check the option Settings > Artificial Intelligence > Google > Dialogflow chatbot.
• If your synchronization was not successful we suggest reviewing our documentation and repeating the synchronization steps to correct any errors. If needed, we provide integration services. Details at the hire us page.
• You selected the wrong agent location.
• Make sure are not using a mega agent.
• Make sure to read the general information.

The settings below are related to the Artificial Intelligence app.

• The automatic sync mode is ready-to-use and does not require any additional settings, Just but credits from https://chat.devad.io/account/?tab=membership Credits Section. Set it at Settings > Artificial Intelligence > OpenAI > Sync mode.
• If you want to activate the chatbot, check Settings > Artificial Intelligence > OpenAI > Chatbot.
• You need to purchase credits to use this option.

The OpenAI (ChatGPT) integration gives your chatbot the ability to answer general questions about almost anything you can imagine. To start using it, follow the steps below.

To set up your first chatbot, follow these steps:

• Complete the synchronization process.
• Enable the Settings > Artificial Intelligence > OpenAI > Chatbot option, and save your changes.
• Your chatbot should now be active. The playground is accessible from the Chatbot area, which you can find by clicking the 🙂 smile icon on the left menu. If the chatbot isn’t working, click the Settings > Artificial Intelligence > OpenAI > Troubleshoot problems button and follow the instructions.
• To further improve your chatbot, explore the training and human takeover sections.

See information about most OpenAI settings here.

This feature is related to the Settings > Artificial Intelligence > OpenAI > Chatbot mode option. It allows you to configure the information OpenAI will use to respond to user messages.

• Only general questions OpenAI will respond only to general questions and questions related to previous user messages in the same conversation, without using any information you provide. This is the default setting.
• Only questions related to your sources OpenAI will only respond to questions related to the information you provide. The user messages will be ignored. You have to first train the chatbot with your sources.
• All questions OpenAI will only to questions related to the information you provide, to general questions, and to questions related to previous user messages in the same conversation. You have to first train the chatbot with your sources. This is the recommended mode.
• Assistant Use this mode if you are using an OpenAI Assistant.

• Set Settings > Artificial Intelligence > OpenAI > Sync mode to Manual and use your own API key.
• You can use multiple assistants by adding their IDs in Settings > Artificial Intelligence > OpenAI Assistants – Department linking and selecting Assistant in Settings > Artificial Intelligence > OpenAI > Chatbot mode. To activate an assistant, both the assistant and the conversations must be assigned to a department.
• The assistant is used only for the chatbot, and smart replies, not for the message rewriting and other features.

The OpenAI chatbot feature functions similarly to Dialogflow, providing automated responses to user messages. Select the Chatbot mode setting to specify the questions that the chatbot is capable of responding to. Utilize the human takeover feature to enable the chatbot to redirect the chat to a human agent as necessary.

The fallback message is sent when OpenAI is unable to understand the user question. If the Dialogflow chatbot is enabled, the fallback message will be turned off and the Dialogflow chatbot’s fallback message will be utilized instead.

The prompt instructs OpenAI on how to respond by providing relevant information that can be utilized to answer user inquiries. To comprehend the process, refer to the example prompts listed below.

If you choose to activate the human takeover feature, you need to tell OpenAI to respond with I don’t know if it is unable to provide an answer to the user’s question. You should always include the following text in the prompt: Respond “I don’t know”, if not sure about the answer.

This prompt instructs OpenAI on how to rewrite a message when the Message rewrite button is active. This prompt should be in English. CHAT.devad.io automatically add the following text when required: and use the user langauge, add greetings.

Replies from the training sources can be utilized with the prompt feature as they are compatible.

This feature automatically fix any spelling mistakes in the agent’s message.

If you are using training data and your chatbot is multilingual, set here the default training data language. Leave it as default if the training data default language is in English.

This feature allow to enable the Smart Reply feature also if the chatbot is not active. If the chatbot is active the Smart Reply feature will use OpenAI automatically.

In the case where Dialogflow is unable to find the appropriate response to the user’s message, this function verifies if there are any spelling errors. If any such errors exist, Dialogflow is prompted again with the correctly spelled version of the message for an accurate response. Although it has a higher priority, this feature can still work together with the Google search spelling correction feature.

This feature adds a button to the text field of the conversation area, click on it to rewrite your message and make it more friendly and professional. Greetings will be added automatically if there is no previous agent messages. If your language is not English, you have to edit your agent/admin profile and set the correct language.

OpenAI supports the use of voice messages through speech recognition. When this option is active, audio messages will be converted to written text.

• You do not need to activate this feature for the chatbot to understand audio messages. The speech recognition feature of the chatbot is always enabled.
• For this feature to work better, the user language should be know. To automatically detect the user’s language, you can enable the language detection feature.
• The text will be displayed alongside the audio player.
• The generated text is compatible with the translation features.

When this option is enabled, the chatbot analyzes and interprets images sent by the users.

• Only GPT-4 models and newer support this feature.
• This feature does not work on localhost, it requires an online server or AWS S3.

When this option is active, the response will automatically include the links to the sources and training data used for generating the answer. To include articles as sources you have first to set the articles page in Settings > Articles > Articles page URL.

When this option is active, you will see a menu in the notes panel. The menu enables the automatic extraction of specific information from the user’s messages like login details, URLs, or even the summary of the conversation.

CHAT.devad.io allows you to adjust various OpenAI parameters such as temperature and logit_bias, for more details visit https://platform.openai.com/docs/api-reference/completions/create. Don’t set any values if you don’t know what these parameters do or OpenAI may stop working.

The Logit bias parameter must be JSON string and the keys must be strings, for example: {“2435”:-100, “640”:-100}.

When this option is active, OpenAI will generate new user questions in real time when you open the chatbot training panel.

Automatically use conversations to train the chatbot at regular intervals. You will find the training data in Chatbot > Training > Conversations. The training is done via cron job every 24 hours. Only user and agent messages are used, chatbot messages are ignored. More details here.

When this option is enabled, OpenAI will recognize the context of the web page from which the user is writing the message. The context includes only the page’s meta title and meta description texts. T his option is supported solely for the chat widget and is not compatible with messaging channels.

With this feature, your chatbot can undergo training using your website, texts, PDF documents and more. Once the training is successfully completed, the chatbot will be able to answer questions related to your contents.

This training process enables you to train the chatbot using PDF and TEXT files.

• To access this feature, navigate to Chatbot > Training > Files.
• Select your files, click the Train chatbot button and await completion of the training process.
• It is only possible to upload files in PDF and TXT formats.
• As soon as the training is completed, the uploaded files are removed.

This training process enables you to train the chatbot using websites.

• To access this feature, navigate to Chatbot > Training > Website.
• Enter the website URLs, click the Train chatbot button and await completion of the training process.
• If you retrain the same website, you must first delete the previous website’s training data; otherwise, only new URLs will be trained.
• You can provide the website URL and all child URLs will be included and crawled, but with large websites, it is more efficient and less prone to errors and infinite link loops to utilize an XML sitemap instead of relying on the website URL. You can create it with a service like https://www.xml-sitemaps.com.
• If you want to train your chatbot using specific pages from your website instead of all of them, you can make use of an XML sitemap. Create one using a tool like https://www.xml-sitemaps.com, and then remove the pages you do not wish to include by editing the file in a text editor. To use the XML sitemap, you need to upload it either onto your server or an external online location. Afterward, add the URL of the sitemap in Chatbot > Training > Website. If your sitemap contains more than 1000 URLs, it’s advisable to split it into multiple files and train the chatbot with one file at a time to prevent server crashes.
• You can upload large files and your XML sitemap with a service like https://tmpfiles.org.

This training process enables you to train the chatbot by adding questions and answers individually.

• To access this feature, navigate to Chatbot > Training > Q&A.
• For more details click here.

This training process enables you to train the chatbot using the articles.

• To train the chatbot add you articles and than click the Train chatbot button. The articles are used as training sources automatically.
• For more details click here.

This training process enables you to train the chatbot using the flows.

• To access this feature, navigate to Chatbot > Flows.
• For more details click here.

This training process enables you to train the chatbot using the conversations from the users and agents.

• To enable this feature, check the Settings > Artificial Intelligence > OpenAI > Use conversations for training option.
• The training data will begin to be generated in the coming days and will be available in the Chatbot > Training > Conversations area.
• While this method is powerful and automated, it can produce low-quality training data if the responses from your human agents or the user messages are unhelpful or incorrect. We strongly recommend reviewing the training data regularly. This method is not recommended for most chatbots. Use the chatbot training panel instead.

Once you have finished training your chatbot, you may want to continue enhancing it. This feature allows you to select conversation messages and use them to add new questions and answers or improve existing ones. You can open the chatbot training panel from the conversation area by hovering the mouse over a message, opening the message’s menu, and selecting Train chatbot.

• If Dialogflow is active, a new Intent will be added to the main Dialogflow agent.
• If OpenAI is active, the OpenAI chatbot will be trained automatically with the new information. You can control the questions and answers generated from this window from Chatbot > Training > Questions and answers.
• The Services to update option let you choose what chatbots to update. When updating a Dialogflow Intent, a new OpenAI question and answer will be generated.
• The training window is not compatible with OpenAI assistants.

This feature allow the chatbot to answers to questions that require real-time information, such as, “What is the temperature in London today?”.

• For more details click here.

• To add new training data, simply train the chatbot again. The previous training data will not be lost, and only the new sources will be added.
• there are character limits for training the chatbot. However, if you are using the PHP or WP version, there are no limits imposed. You can view the character limits here.
• The embedding model is essential for training your chatbot and handling all user messages. We currently use the text-embedding-3-small model. It is necessary for these scenarios and cannot be disabled or changed. You can find pricing information at https://openai.com/pricing. Check out the pricing for the text-embedding-3-small model in the Embedding models section.
• Go to Chatbot > Training > Information, and click the Delete all training data button to remove all previous training data for the chatbot.
• The embeddings are stored as JSON files in the CHAT.devad.io uploads folder and are secured using the password-by-filename approach.

just enable the Settings > Artificial Intelligence > OpenAI > Training via cron job option and the cron job will be activated. You can disregard the instructions below.

To automatically train the chatbot with your website content at regular intervals, create a cron job that runs the URL https://chat.devad.io/include/api.php?open-ai-training=true, or use the command */59 * * * * wget https://chat.devad.io/include/api.php?open-ai-training=true to run it via a command. Replace https://chat.devad.io with your Installation URL, get it from Settings > Miscellaneous > Installation URL. use this URL: https://chat.devad.io/script/include/api.php?open-ai-training=true&cloud=API-TOKEN and replace API-TOKEN with your API token.

• the cron job can be executed at most once every 7 days.
• We strongly recommand providing an XML sitemap instead of the website URL for performance reasons.
• Automatic training is limited to websites; files, Q&A, and articles are excluded. Re-training will delete the previous website training data.

If your user base is multilingual, you can train the chatbot with content in multiple languages and limit the chatbot to retrieve answers only from the sources in the user’s language. To activate this feature, check the Settings > Artificial Intelligence > OpenAI > Multilingual Training Sources option.

• Files Files currently support only one language.
• Websites The language of the website is detected automatically. For CHAT.devad.io to comprehend the language of your web pages, the must contain the attribute lang.
• Q&A Q&A currently support only one language.
• Articles All article languages are used automatically.
• Conversations If automatic translation is active, only messages in the agent’s language will be used.

The information below is related to the Question and Answers section of the chatbot training area. Add questions and answers to the chatbot to improve its performance. The chatbot will use this information to respond to user inquiries.

Enter the user messages that will trigger the answer. Add as many question variations as necessary. For example the questions to the answer I’m a chatbot! could be Who are you?, What are you?, Are you a bot?.

Enter the text that will be used to answer the user question.

For more details go here.

Set the specified user values when the question is asked. You will see such values in the user details panel. You can use the following merge fields to assign values extracted from the user messages. Include these fields in the answer and they will be replaced with the actual values: {language}. You can also use this feature to perform actions like assigning departments, agents, and tags to the conversation.

• If OpenAI is not working, click here.
• If Dialogflow is active, the OpenAI query is performed only if the chatbot does not know the answer to the user’s question and if the length of the user’s message is greater than 4 characters.
• The following settings are compatible with OpenAI: smart reply, human takeover, disable for the tickets area, disable during office hours, bot response delay, reply to user emails, reply to user text messages.
• The following Google settings are compatible with OpenAI: multilingual via translation, automatic translation, language detection.
• Set the OpenAI chatbot language from Settings > Chat > Language. Set it to Multilingual if your website supports multiple languages or if your users speak different languages. If you are using messaging channels like WhatsApp, or Instagram, you must detect the user language via language detection. For more details click here.
• If a human takes control, the OpenAI chatbot is deactivated, and is remains deactivated also if the agent goes offline. The Dialogflow chatbot continues to function whenever necessary.
• The default model is gpt-5-mini.
• Consecutive user messages are treated as a single message by the chatbot, resulting in one unified reply

The settings below are related to the Artificial Intelligence app.

• The automatic sync mode is ready-to-use and does not require any additional settings, Just but credits from https://chat.devad.io/account/?tab=membership Credits Section. Set it at Settings > Artificial Intelligence > OpenAI > Sync mode.
• If you want to activate the chatbot, check Settings > Artificial Intelligence > OpenAI > Chatbot.
• You need to purchase credits to use this option.

The OpenAI (ChatGPT) integration gives your chatbot the ability to answer general questions about almost anything you can imagine. To start using it, follow the steps below.

To set up your first chatbot, follow these steps:

• Complete the synchronization process.
• Enable the Settings > Artificial Intelligence > OpenAI > Chatbot option, and save your changes.
• Your chatbot should now be active. The playground is accessible from the Chatbot area, which you can find by clicking the 🙂 smile icon on the left menu. If the chatbot isn’t working, click the Settings > Artificial Intelligence > OpenAI > Troubleshoot problems button and follow the instructions.
• To further improve your chatbot, explore the training and human takeover sections.

See information about most OpenAI settings here.

This feature is related to the Settings > Artificial Intelligence > OpenAI > Chatbot mode option. It allows you to configure the information OpenAI will use to respond to user messages.

• Only general questions OpenAI will respond only to general questions and questions related to previous user messages in the same conversation, without using any information you provide. This is the default setting.
• Only questions related to your sources OpenAI will only respond to questions related to the information you provide. The user messages will be ignored. You have to first train the chatbot with your sources.
• All questions OpenAI will only to questions related to the information you provide, to general questions, and to questions related to previous user messages in the same conversation. You have to first train the chatbot with your sources. This is the recommended mode.
• Assistant Use this mode if you are using an OpenAI Assistant.

• Set Settings > Artificial Intelligence > OpenAI > Sync mode to Manual and use your own API key.
• You can use multiple assistants by adding their IDs in Settings > Artificial Intelligence > OpenAI Assistants – Department linking and selecting Assistant in Settings > Artificial Intelligence > OpenAI > Chatbot mode. To activate an assistant, both the assistant and the conversations must be assigned to a department.
• The assistant is used only for the chatbot, and smart replies, not for the message rewriting and other features.

The OpenAI chatbot feature functions similarly to Dialogflow, providing automated responses to user messages. Select the Chatbot mode setting to specify the questions that the chatbot is capable of responding to. Utilize the human takeover feature to enable the chatbot to redirect the chat to a human agent as necessary.

The fallback message is sent when OpenAI is unable to understand the user question. If the Dialogflow chatbot is enabled, the fallback message will be turned off and the Dialogflow chatbot’s fallback message will be utilized instead.

The prompt instructs OpenAI on how to respond by providing relevant information that can be utilized to answer user inquiries. To comprehend the process, refer to the example prompts listed below.

If you choose to activate the human takeover feature, you need to tell OpenAI to respond with I don’t know if it is unable to provide an answer to the user’s question. You should always include the following text in the prompt: Respond “I don’t know”, if not sure about the answer.

This prompt instructs OpenAI on how to rewrite a message when the Message rewrite button is active. This prompt should be in English. CHAT.devad.io automatically add the following text when required: and use the user langauge, add greetings.

Replies from the training sources can be utilized with the prompt feature as they are compatible.

This feature automatically fix any spelling mistakes in the agent’s message.

If you are using training data and your chatbot is multilingual, set here the default training data language. Leave it as default if the training data default language is in English.

This feature allow to enable the Smart Reply feature also if the chatbot is not active. If the chatbot is active the Smart Reply feature will use OpenAI automatically.

In the case where Dialogflow is unable to find the appropriate response to the user’s message, this function verifies if there are any spelling errors. If any such errors exist, Dialogflow is prompted again with the correctly spelled version of the message for an accurate response. Although it has a higher priority, this feature can still work together with the Google search spelling correction feature.

This feature adds a button to the text field of the conversation area, click on it to rewrite your message and make it more friendly and professional. Greetings will be added automatically if there is no previous agent messages. If your language is not English, you have to edit your agent/admin profile and set the correct language.

OpenAI supports the use of voice messages through speech recognition. When this option is active, audio messages will be converted to written text.

• You do not need to activate this feature for the chatbot to understand audio messages. The speech recognition feature of the chatbot is always enabled.
• For this feature to work better, the user language should be know. To automatically detect the user’s language, you can enable the language detection feature.
• The text will be displayed alongside the audio player.
• The generated text is compatible with the translation features.

When this option is enabled, the chatbot analyzes and interprets images sent by the users.

• Only GPT-4 models and newer support this feature.
• This feature does not work on localhost, it requires an online server or AWS S3.

When this option is active, the response will automatically include the links to the sources and training data used for generating the answer. To include articles as sources you have first to set the articles page in Settings > Articles > Articles page URL.

When this option is active, you will see a menu in the notes panel. The menu enables the automatic extraction of specific information from the user’s messages like login details, URLs, or even the summary of the conversation.

CHAT.devad.io allows you to adjust various OpenAI parameters such as temperature and logit_bias, for more details visit https://platform.openai.com/docs/api-reference/completions/create. Don’t set any values if you don’t know what these parameters do or OpenAI may stop working.

The Logit bias parameter must be JSON string and the keys must be strings, for example: {“2435”:-100, “640”:-100}.

When this option is active, OpenAI will generate new user questions in real time when you open the chatbot training panel.

Automatically use conversations to train the chatbot at regular intervals. You will find the training data in Chatbot > Training > Conversations. The training is done via cron job every 24 hours. Only user and agent messages are used, chatbot messages are ignored. More details here.

When this option is enabled, OpenAI will recognize the context of the web page from which the user is writing the message. The context includes only the page’s meta title and meta description texts. T his option is supported solely for the chat widget and is not compatible with messaging channels.

With this feature, your chatbot can undergo training using your website, texts, PDF documents and more. Once the training is successfully completed, the chatbot will be able to answer questions related to your contents.

This training process enables you to train the chatbot using PDF and TEXT files.

• To access this feature, navigate to Chatbot > Training > Files.
• Select your files, click the Train chatbot button and await completion of the training process.
• It is only possible to upload files in PDF and TXT formats.
• As soon as the training is completed, the uploaded files are removed.

This training process enables you to train the chatbot using websites.

• To access this feature, navigate to Chatbot > Training > Website.
• Enter the website URLs, click the Train chatbot button and await completion of the training process.
• If you retrain the same website, you must first delete the previous website’s training data; otherwise, only new URLs will be trained.
• You can provide the website URL and all child URLs will be included and crawled, but with large websites, it is more efficient and less prone to errors and infinite link loops to utilize an XML sitemap instead of relying on the website URL. You can create it with a service like https://www.xml-sitemaps.com.
• If you want to train your chatbot using specific pages from your website instead of all of them, you can make use of an XML sitemap. Create one using a tool like https://www.xml-sitemaps.com, and then remove the pages you do not wish to include by editing the file in a text editor. To use the XML sitemap, you need to upload it either onto your server or an external online location. Afterward, add the URL of the sitemap in Chatbot > Training > Website. If your sitemap contains more than 1000 URLs, it’s advisable to split it into multiple files and train the chatbot with one file at a time to prevent server crashes.
• You can upload large files and your XML sitemap with a service like https://tmpfiles.org.

This training process enables you to train the chatbot by adding questions and answers individually.

• To access this feature, navigate to Chatbot > Training > Q&A.
• For more details click here.

This training process enables you to train the chatbot using the articles.

• To train the chatbot add you articles and than click the Train chatbot button. The articles are used as training sources automatically.
• For more details click here.

This training process enables you to train the chatbot using the flows.

• To access this feature, navigate to Chatbot > Flows.
• For more details click here.

This training process enables you to train the chatbot using the conversations from the users and agents.

• To enable this feature, check the Settings > Artificial Intelligence > OpenAI > Use conversations for training option.
• The training data will begin to be generated in the coming days and will be available in the Chatbot > Training > Conversations area.
• While this method is powerful and automated, it can produce low-quality training data if the responses from your human agents or the user messages are unhelpful or incorrect. We strongly recommend reviewing the training data regularly. This method is not recommended for most chatbots. Use the chatbot training panel instead.

Once you have finished training your chatbot, you may want to continue enhancing it. This feature allows you to select conversation messages and use them to add new questions and answers or improve existing ones. You can open the chatbot training panel from the conversation area by hovering the mouse over a message, opening the message’s menu, and selecting Train chatbot.

• If Dialogflow is active, a new Intent will be added to the main Dialogflow agent.
• If OpenAI is active, the OpenAI chatbot will be trained automatically with the new information. You can control the questions and answers generated from this window from Chatbot > Training > Questions and answers.
• The Services to update option let you choose what chatbots to update. When updating a Dialogflow Intent, a new OpenAI question and answer will be generated.
• The training window is not compatible with OpenAI assistants.

This feature allow the chatbot to answers to questions that require real-time information, such as, “What is the temperature in London today?”.

• For more details click here.

• To add new training data, simply train the chatbot again. The previous training data will not be lost, and only the new sources will be added.
• there are character limits for training the chatbot. However, if you are using the PHP or WP version, there are no limits imposed. You can view the character limits here.
• The embedding model is essential for training your chatbot and handling all user messages. We currently use the text-embedding-3-small model. It is necessary for these scenarios and cannot be disabled or changed. You can find pricing information at https://openai.com/pricing. Check out the pricing for the text-embedding-3-small model in the Embedding models section.
• Go to Chatbot > Training > Information, and click the Delete all training data button to remove all previous training data for the chatbot.
• The embeddings are stored as JSON files in the CHAT.devad.io uploads folder and are secured using the password-by-filename approach.

just enable the Settings > Artificial Intelligence > OpenAI > Training via cron job option and the cron job will be activated. You can disregard the instructions below.

To automatically train the chatbot with your website content at regular intervals, create a cron job that runs the URL https://chat.devad.io/include/api.php?open-ai-training=true, or use the command */59 * * * * wget https://chat.devad.io/include/api.php?open-ai-training=true to run it via a command. Replace https://chat.devad.io with your Installation URL, get it from Settings > Miscellaneous > Installation URL. use this URL: https://chat.devad.io/script/include/api.php?open-ai-training=true&cloud=API-TOKEN and replace API-TOKEN with your API token.

• the cron job can be executed at most once every 7 days.
• We strongly recommand providing an XML sitemap instead of the website URL for performance reasons.
• Automatic training is limited to websites; files, Q&A, and articles are excluded. Re-training will delete the previous website training data.

If your user base is multilingual, you can train the chatbot with content in multiple languages and limit the chatbot to retrieve answers only from the sources in the user’s language. To activate this feature, check the Settings > Artificial Intelligence > OpenAI > Multilingual Training Sources option.

• Files Files currently support only one language.
• Websites The language of the website is detected automatically. For CHAT.devad.io to comprehend the language of your web pages, the <html> must contain the attribute lang.
• Q&A Q&A currently support only one language.
• Articles All article languages are used automatically.
• Conversations If automatic translation is active, only messages in the agent’s language will be used.

The information below is related to the Question and Answers section of the chatbot training area. Add questions and answers to the chatbot to improve its performance. The chatbot will use this information to respond to user inquiries.

Enter the user messages that will trigger the answer. Add as many question variations as necessary. For example the questions to the answer I’m a chatbot! could be Who are you?, What are you?, Are you a bot?.

Enter the text that will be used to answer the user question.

For more details go here.

Set the specified user values when the question is asked. You will see such values in the user details panel. You can use the following merge fields to assign values extracted from the user messages. Include these fields in the answer and they will be replaced with the actual values: {language}. You can also use this feature to perform actions like assigning departments, agents, and tags to the conversation.

• If OpenAI is not working, click here.
• If Dialogflow is active, the OpenAI query is performed only if the chatbot does not know the answer to the user’s question and if the length of the user’s message is greater than 4 characters.
• The following settings are compatible with OpenAI: smart reply, human takeover, disable for the tickets area, disable during office hours, bot response delay, reply to user emails, reply to user text messages.
• The following Google settings are compatible with OpenAI: multilingual via translation, automatic translation, language detection.
• Set the OpenAI chatbot language from Settings > Chat > Language. Set it to Multilingual if your website supports multiple languages or if your users speak different languages. If you are using messaging channels like WhatsApp, or Instagram, you must detect the user language via language detection. For more details click here.
• If a human takes control, the OpenAI chatbot is deactivated, and is remains deactivated also if the agent goes offline. The Dialogflow chatbot continues to function whenever necessary.
• The default model is gpt-5-mini.
• Consecutive user messages are treated as a single message by the chatbot, resulting in one unified reply

The information below is related to the chatbot flows area. Flows allows you to esely create conversation flows powered by the chatbot. Use them to guide the user toward a specific goal with a series of pre-defined messages.

Flow blocks

• Start: Use the start block to set when the flows should start. It can be everytime the user start a new conversation, when it sends a specific message, or on page load. If you set conditions, the flow will only start when all conditions are met. If you set a depertment, the flow will only start for conversations assigned to that department. If you set a source, the flow will only start for conversations from that source.
• Send message: Send a message to the user.
• Send choices: Send a list of buttons to the user or allow it to choose one. When conversational mode is enabled, buttons are hidden, the chatbot sends only text, and users select options by replying with text. The AI interprets the message and selects the corresponding option, continuing the flow as if the button were pressed. This creates a more natural, chat-like experience and is automatically activated, only when needed, on messaging channels such as WhatsApp and Instagram. If the user’s reply doesn’t match any option, a fallback message with the available choices will be sent. You can add variations to the button texts by separating them with the | char, for example: Yes|Yeah|Sure. They will help the AI to understand the user reply.
• Send video: Send a video to the user.
• Get user details: Get the user details and store them in CHAT.devad.io. You will see such values in the user details panel. You can leave the description field empty for default details, but it’s required if using custom user fields. Note that user details will not be saved if you test this flow in the playground, as the user there is temporary. To see details saved, test the flow with a real user.

  

• Set data: Set the specified user values when the block is executed. You will see such values in the user details panel.
• Actions: Execute the specified actions when the block is executed.
• Conditions: Use it to create different branches in the flow. If the conditions are met, the flow will follow the branch set as true, otherwise the one set as false.
• Rest API: Use it to send data to your server. The body must be a JSON array. Details like user ID and conversation ID are automatically included in the data sent to your server under the sb key. Use the save response section to save specified user details with values from your server response. Use the JSON dot notation. Our support doesn’t include assistance with this feature, as it is for advanced users and requires custom code on your server. For help with this, feel free to hire us.
• Tools calling: For more details go here.
• Flow connector: Connect the flow to another flow and start it.

• Flows can be multilingual. Add translations for messages, button texts, and other content in the translations area. You can also use the multilingual via translation feature for automatic translations. If the default language of your flows is not English you have also to set the default language under Settings > Artificial Intelligence > OpenAI > Training Sources Language.
• Users can move back to earlier steps and update previously entered details in a conversational manner. For example, they might say “Sorry, I entered the wrong email”, “I need to update my email and phone number”, or even a general message like “Sorry, I entered the wrong details, go back”, which will return them to the previous step.

Q: What are Flows Builder?
Flows are sequences of interactions between the user and the chatbot that guide the user through a series of questions and answers.

Q: How can I start a Flow?
Use the Start block to set when the Flows should start, such as when a user starts a new conversation, sends a specific message, or on page load. Flows can start only when all set conditions are met.

Q: What action blocks are available in Flows?
Available blocks include Send message, Send button list, Send video, Get user details, Set data, Actions, Conditions, and Rest API.

Q: How do Conditions work in Flows?
Conditions create different branches in the Flow. If a condition is met, the Flow follows the true branch; otherwise, it follows the false branch.

Q: Can Flows collect user information?
Yes, using the Get user details block, Flows can gather and store user information.

Q: How can I send data to my server from a Flow?
Use the Rest API block to send data via a JSON array to your server. User details are included automatically under the sb key.

Q: Are there predefined Flows?
Yes, CHAT App automatically generates flows such as Registration and Follow-up flows based on specific settings.

Q: Can I customize Flows according to my needs?
Yes, you can create custom Flows combining various blocks and conditions to guide your users toward specific goals.

Q: Is technical knowledge required to use the Rest API block in Flows?
Yes, the Rest API block requires advanced knowledge and custom server code for proper integration.

Q: Can users take control from an automated Flow and talk to a human agent?
Yes, Flows support a human takeover feature where users can switch from the automated flow to live human support.

Q: How do I track the performance of my Flows?
You can monitor Flow engagement and conversion statistics in the analytics section of Support Board to optimize your setup.

Tools calling allows to connect the chatbot to external tools and systems to retrive information needed to answer the user. The chatbot will query your server and return the information from your server to the user. The data sent to your server is in the body and it includes the user input, user ID, and conversation ID. Tools calling is used by Q&A and Flows. More details here. Our support doesn’t include assistance with this feature, as it is for advanced users and requires custom code on your server. For help with this, feel free to hire us.

• URL: Enter the URL of the API endpoint that will supply the necessary values for the function.
• Headers: If you are setting up a Q&A, enter key-value header parameters, separated by commas. E.g. apikey:123345, json:true. If you are setting up a flow, enter add key-value header parameters by clicking the Add new item button.
• Properties: Enter values that the user must provide to the chatbot. For example a city, a tracking number, etc. The chatbot will ask the user for these values. If you already know all the possible values, you can enter them in the Allowed values field.

CHAT.devad.io will send the following information to your server. If you use the POST method, it will be included in the JSON body, if you use the GET method, it will be included in the header.

{
    "sb": {
        "user_id": "123",
        "conversation_id": "123",
        "user_language": "es"
    },
    "arguments": {}
}

The arguments array contains the values provided by the user. The keys are the name converted to kebab case, for example if the property name is Order Number, the key will be order-number. The user_id is the ID of the user in CHAT.devad.io and conversation_id is the ID of the conversation. You can use these IDs to retrieve more information about the user and the conversation via the REST API.

Your server must returns a JSON array with the values required by the chatbot. Include success: true only when the request is successful and the expected information is returned. Do not include it if the information cannot be retrieved (e.g., when an invalid order number is provided). See the example below for more details.

{
    "order_status": "Delivered 2 hours and 25 minutes ago",
    "success": true
}

The settings below are related to the Artificial Intelligence app.

To start using the Google AI services and Dialogflow follow the steps below.

• Click Synchronize now and complete the procedure.
• If you want to activate the Dialogflow chatbot, check Settings > Artificial Intelligence > Google > Dialogflow chatbot. Also, you have to enter your chatbot Project ID or Agent Name, to get it follow the steps below.
• You need to purchase credits to use this option.

• Enable the CHAT.devad.io > Settings > Artificial Intelligence > Google > Dialogflow Chatbot option and save the changes.
• Go to console.cloud.google.com and sign in.
• Select or create a project by clicking the Select a project button on top-left. Name the project as you want.
• Activate the Dialogflow API by entering Dialogflow API on the top search bar. Click Dialogflow API and then click Enable. Do the same for the Cloud Natural Language API, Cloud Translation API, and Google Calendar API.
• Select the project and the go to Left menu > APIs and services > OAuth consent screen. Select External and click Create. In App name enter what you want, in User support email and Developer contact information enter your email. Click Save and continue.
• In the Data access area, click Add or remove scopes, scroll bottom and into the Manually add scopes area enter https://www.googleapis.com/auth/dialogflow,https://www.googleapis.com/auth/cloud-language,https://www.googleapis.com/auth/cloud-translation,https://www.googleapis.com/auth/calendar. Click Add to table and then Update and Save and continue.
• In the Audience area, click Add users and add your Google email, use the same email as the currently logged in account. Click Save and continue. Click PUBLISH APP. There is no need to complete the review process, leave it in the pending review state.
• Go to Left menu > APIs and services > Credentials and click Create credentials, select OAuth client ID. As Application type select Web application. Enter any name you want. In Authorised redirect URI enter the redirect URL, get it from CHAT.devad.io > Settings > Artificial Intelligence > Google > Authorised redirect URI. Click Create.
• Copy Client ID and Client Secret and paste them into CHAT.devad.io > Settings > Artificial Intelligence > Dialogflow. Save the settings.
• Click CHAT.devad.io > Settings > Artificial Intelligence > Google > Synchronize. Login with the same Google account you have used till now. On the next screen click Continue. On the next screen select all scopes and click Continue.
• Copy the Refresh token and paste it into CHAT.devad.io > Settings > Artificial Intelligence > Google > Refresh token.
• You are done! If you want to activate the Dialogflow chatbot, check Settings > Artificial Intelligence > Google > Dialogflow chatbot. Also, you have to enter your chatbot Project ID or Agent Name, to get it follow the steps below. Note that the app does not need to be approved by Google.
• If you are a Google Workspace user, go to https://admin.google.com/ and click Google Cloud Session control. Set Re-authentication policy to Never require re-authentication.

The feature Artificial Intelligence > Google > Multilingual checks if there is a Dialogflow agent in the user’s language and activate it.

• For this feature to work the user language must be know. The user language is based on the language user detail of the user if set, otherwise on the user browser language. The language can also be detected with the language detection feature.

The automatic translation feature automatically translates user messages into agent language and agent messages into user language. To enable it check the option Settings > Artificial Intelligence > Automatic translation. If you are using the cloud version and Artificial Intelligence > Google > Sync mode is set to Automatic, the multilingual features will work automatically. Otherwise you have to complete the synchronization and the setup below. The multilingual via translation and language detection features also require these steps.

• Log in to https://console.cloud.google.com with your Google account and select the project of your Dialogflow Agent.
• On the top search bar type cloud translation, select the Cloud Translation API service and enable it. Please note that this is a paid service with a free tier, additional charges may occur.
• Enable the billing by clicking Left menu > Billing and by enabling a billing account with a valid payment method.

• The user messages in the admin area are translated automatically in real-time to match the agent language.
• The agent messages are translated automatically in real-time to match the user language.
• Agents can view the original message by opening the message menu and by clicking View original message.
• The agent language is based on the language user detail of the agent if set, otherwise on the browser language, or admin area language.
• The user language is based on the language user detail, if set, otherwise on chat language, if set, otherwise on the browser language. The language can also be detected with the language detection feature.
• The notifications are also translated.
• To avoid translating a string, enclose it with the characters ` or “`.

The feature at Settings > Artificial Intelligence > Multilingual via translation automatically translates user messages into the default language of Dialogflow or OpenAI, and translates Dialogflow or OpenAI messages into the language spoken by the user. Additionally, this feature translates all text displayed within the chat, such as the chatbot’s rich messages, articles, registration forms, and pop-up notifications. To enhance performance and minimize translation costs, the translations are automatically integrated into the translation files. Combine this feature with the language detection feature for optimal results.

• If English is one of the languages, English must be the default language, the original texts must be in English.
• If you are using OpenAI with training data, set the default training data language under Settings > Artificial Intelligence > OpenAI > Training Sources Language. Leave it as default if the training data default language is in English.

Detect the language of the user’ messages and change the user language and Dialogflow agent language accordingly, if available, otherwise, show a fallback message. You can use the following merge fields in the message: {language_name}.

• The user message must be at least 2 words long.
• Language detection is executed only for the first 2 user messages of a conversation.
• As long as the OpenAI chatbot is operational and programmed to respond to generic inquiries, the fallback message will never be dispatched, since OpenAI will consistently provide answers to any use message.

The Google search feature at Settings > Artificial Intelligence > Google search gives your chatbot the ability to search for answers on Google. This feature is helpful for providing answers to questions that require real-time information.

• Register at https://programmablesearchengine.google.com/.
• Create a search and setup it is as you want. We recommend to add only your website and Wikipedia if you want your chatbot to reply to general questions, leave disabled the option Search the entire web. Use the Entities option to exclude invalid results.
• Go to Edit search engine > Setup > Basic and copy the Search engine ID value, paste it in CHAT.devad.io.
• To get the API key visit https://developers.google.com/custom-search/v1/overview and click Get a key.

In the case where Dialogflow is unable to find the appropriate response to the user’s message, this function verifies if there are any spelling errors. If any such errors exist, Dialogflow is prompted again with the correctly spelled version of the message for an accurate response. Although it has a lower priority, this feature can still work together with the OpenAI Dialogflow spelling correction feature.

The Entities setting analyze the user’s message and recognize and extract entities like cities, events, dates, and more. Use it to exclude invalid results returned by Google search. To enable this setting follow the steps below.

• Log in to https://console.cloud.google.com with your Google account and select the project of your Dialogflow Agent.
• Enter Cloud Natural Language API in the search bar at the top, select Cloud Natural Language API and enable the API .
• Enable the billing by clicking Left menu > Billing and by enabling a billing account with a valid payment method. Enable billing for the project of your Dialogflow agent.

• The Google search is performed only if the chatbot does not know the answer to the user’s question and if the length of the user’s message is greater than 4 characters.
• If the Google search returns a result, the Dialogflow context google-search is automatically activated. The context contains the attribute link which is the website’s link of the Google search result. Use the context to create a new intent that provides the link, if the user sends a message like tell me more or I want to know more.
• Google search is not required to activate the spelling correction. You can disable Google search and activate only spelling correction.
• Google search is compatible with the OpenAI chatbot.

🛠️ Google Calendar & AI Integration FAQ

Connectivity & Syncing

Q: Why is my Google Calendar not syncing with CHAT App (CHAT.devad.io)? Ensure your Google account authorization is active and has the correct permissions. This issue can also stem from incorrect OAuth credentials, expired tokens, or insufficient permissions granted during the initial setup. Check your connection and reauthorize if necessary.

Q: Why do my appointments not appear correctly in Google Calendar? This is often caused by time zone mismatches or selecting the wrong calendar in the CHAT App (CHAT.devad.io) settings. Verify that your dashboard settings match your preferred local time zone and specific calendar ID.

Q: Can I create appointments in CHAT App (CHAT.devad.io) that automatically show in Google Calendar? Yes. The platform integrates directly with Google Calendar to create, display, and update appointments automatically the moment they are scheduled via the chat interface.

Q: Why do Google contacts or calendar events sometimes not update immediately? Sync delays can occur due to API rate limits or temporary network fluctuations. Performing a manual sync or refreshing the dashboard usually resolves this.

AI & Automation Features

Q: Why am I not receiving AI-generated appointment reminders? Check your notification settings within CHAT App (CHAT.devad.io). Ensure that email or SMS reminders are enabled and that the lead’s contact details are correctly formatted.

Q: How does CHAT App (CHAT.devad.io) handle appointment rescheduling? Users can reschedule appointments naturally via chat. The system automatically updates the linked Google Calendar and sends out notifications to all involved parties to keep everyone aligned.

Q: Can AI features suggest optimal appointment times? Yes. The AI analyzes your real-time availability and recommends specific meeting times to the user, significantly improving scheduling efficiency and reducing back-and-forth messaging.

Q: How do AI features like Smart Reply or Human Takeover work? Smart Reply provides AI-powered suggested responses for quick interactions, while Human Takeover allows a seamless transition from the bot to a human agent for complex queries that require a personal touch.

Q: What should I do if the AI-generated answers are inaccurate or irrelevant? Adjust your programmable search engine setup within the app. Ensure you include only trusted domains (like your official website) and use Entity filters to exclude invalid or off-topic results.

Technical Troubleshooting & API

Q: How can I fix OAuth consent screen errors during setup? Ensure all required scopes (such as Dialogflow, Cloud Language, and Cloud Translation) are added. The OAuth consent screen must be published in the Google Cloud Console, even if it is still in the “pending review” state.

Q: What should I do if Google API requests exceed the quota limit? Review your API usage and optimize your query frequency. If your volume remains high, you can request a quota increase via the Google Cloud Console to prevent synchronization delays.

Q: What happens if the Google Workspace re-authentication policy interferes with integration? To avoid service disruptions, set the Cloud Session control’s Re-authentication policy to “Never require re-authentication” within your Google Workspace admin settings.

Privacy & Reliability

Q: Are there privacy concerns with syncing appointments? CHAT App (CHAT.devad.io) follows GDPR and global privacy laws. The system only syncs data strictly necessary for scheduling appointments and requires explicit user consent.

Q: Why am I experiencing delays in AI-generated follow-ups? Delays can stem from server loads, connectivity issues, or AI processing errors. We recommend monitoring the system status and ensuring you are using the latest version of the app for optimal performance.

Comprehensive User Management

Efficiently administering your user base is crucial for support operations. You can fully manage users directly from the Users area located in the left-hand menu of your admin dashboard.

Importing and Searching Users

To bulk onboard users, navigate to Settings > Users > Import users. The system currently supports CSV files exclusively. A template CSV file is available for download within that section to guide your formatting. In this template, the first row serves as the header. If you wish to import specific data points like “Height” or “Hair color,” you must first add them as Custom User Fields via Settings > Users > Custom fields.

Locating specific individuals is streamlined through the search function. You can query the database using the user’s name, surname, email address, or any defined custom fields.

Deleting Users

To remove a single user, open their User Edit box and click the Delete user button. For bulk actions, navigate to the Users table, select multiple users via the checkboxes, and click the Delete icon in the top right corner.

Permanent Deletion! When a user is deleted, all their conversations, messages, and attachments (including those on AWS S3) are permanently removed. Visitors are automatically deleted every 24 hours.

If a previously deleted user returns to your website, a completely new user profile is automatically created for them.

Merging Users & Custom Columns

Merging Profiles: You can consolidate two user profiles directly from the user table. Simply select two users and click the Merge Users button at the top. All conversations will be combined under the new user account, and the system will intelligently merge relevant personal details.

Additional Table Columns: To view more data at a glance, go to Settings > Admin > Users table additional columns. Add columns using the slug of the user detail. The slug must be lowercase with spaces replaced by hyphens (e.g., “Date of birth” becomes date-of-birth).

User Types & Roles

Manage Agents and Admins

You can create, manage, and delete agents and administrators directly from the Users area. To create a new team member, click the Add user button in the top right corner.

• Privileges: Configure permissions via Settings > Admin > Agent privileges.
• Supervisors: Create special agents with extended privileges at Settings > Admin > Supervisor. You can add multiple supervisors by entering comma-separated Admin IDs.
• WordPress Integration: Upon activating the plugin, an admin account is automatically created matching your current WordPress credentials.

Collecting User Details & Registration

Gathering user data such as names and emails is essential for follow-up. This can be achieved via Chatbot Flows, Follow-up messages, or the Registration Form.

Registration & Login Forms

The registration form acts as a pre-chat gate, requiring users to enter specific details before engaging. You can configure this in Settings > Users.

• Pre-Chat Form: You can limit the form to specific fields (e.g., just the email or name) by selecting “Registration form” under the Require registration option and enabling specific fields in the Registration fields list.
• Login Logic: The login form appears only if the email field is enabled. If the user system is set to “WordPress,” the password field is mandatory.
• Duplicate Emails: If a user attempts to register with an existing email, an OTP (One-Time Password) is sent to facilitate login. This prevents duplicate registrations, which are rare in real-world scenarios as users typically stay logged in.

OTP Verification

The OTP feature validates emails by sending a one-time code that the user must enter. Enable this via Settings > Users > Email verification. Even if disabled, the OTP system triggers automatically if a user tries to register an already existing email.

Advanced Authentication

Login Verification URL

This feature allows authentication via an external source. The system sends a request to your specified URL (Settings > Users > Login verification URL), appending the `email` and `password` as parameters.
Example: https://example.com/[email protected]&password=123.

The external URL must respond with a JSON object formatted as follows:

{
"first_name": "John",
"last_name": "Doe",
"email": "[email protected]",
"profile_image": "https://chat.devad.io/user.svg",
"department": null,
"password": "",
"details": {
"location": [ "Location", "New York, United States" ],
"country_code": [ "Country code", "America/New_York" ]
}
}

Note: The value first_name is required.

Login Link & Forgot Password

If enabled (under “Require registration”), users can click “Forgot password” to receive a Magic Login Link via email. Clicking this link logs them in automatically. You can customize the email template at Settings > Users > Login link email.

Real-Time Monitoring & Notifications

Online Notifications!
To receive notifications for online users (Visitors and Leads included), enable Pusher in settings. Note: Notifications are sent once per user every 24 hours.

New users populate the user table in real time. To view all active visitors, enable Settings > Users > Register all visitors.

Away Mode: If an agent or admin is inactive for 10 minutes (no clicks, movements, or key presses), their status is automatically set to “Offline”. This requires Pusher to be enabled and does not function on mobile devices.

In the fiercely competitive landscape of modern e-commerce, every website visitor represents a valuable opportunity, and each abandoned cart signifies a significant loss in potential revenue. Standard, reactive customer support is no longer sufficient to captivate and convert today’s discerning online shoppers. Businesses require an intelligent, proactive engagement system that not only resolves queries but actively drives sales and builds brand loyalty. CHAT.devad.io is engineered to be precisely that solution, transforming your customer interactions into a high-performance sales and marketing engine. By leveraging an advanced AI Agent, deep, native integrations with leading e-commerce platforms like Shopify, WooCommerce, and OpenCart, and powerful omnichannel marketing tools like WhatsApp Broadcasting, CHAT.devad.io empowers you to dramatically increase sales, slash cart abandonment rates, and cultivate lasting customer relationships.

AI-Powered Chatbot in CHAT.devad.io

Ecommerce, Lead Gen, & Customer Support Supercharged!
For ecommerce lead generation, deploy intelligent bots that qualify prospects, capture details, and nurture conversions 24/7 with human-like flows.
For customer support, automate routine queries, escalate seamlessly to agents, and deliver instant, multilingual resolutions—slashing workloads while boosting satisfaction.

The AI Agentic Chatbot in CHAT.devad.io

Elevate your site with CHAT.devad.io’s cutting-edge AI Agentic Chatbot, built on embedding-driven Retrieval-Augmented Generation (RAG). Transform static content into dynamic, smart dialogues that captivate and convert.

This isn’t your basic responder—it’s a sophisticated RAG powerhouse. Powered by OpenAI’s text-embedding-3-small, it absorbs your unique data from docs, web links, sitemaps, and chat logs. Result? Context-aware retrieval of precise info, delivering spot-on, natural replies to any query.

Smart Chatbots Powered by OpenAI and Google

Accelerate fixes and streamline talks by fusing OpenAI, Google AI, and premium features. Deploy in minutes for effortless automation.

Automated Communication

Bots handle queries independently when equipped with answers. Unsure? Seamlessly hand off to live agents for takeover.

• Automated communication
• Easy 30-second installation
• Custom chatbot reply delay
• Human-like conversations

Easy to Use. Easy Chatbot Setup.

No Coding Skills Required
Auto-train on your site via Q&A pairs, PDFs, flows, and beyond.

Learn While You Build
Kick off simple, then layer in contexts and entities as you grow.

Online Guides and Videos
Tap rich OpenAI, Google, and bot tutorials plus demos.

Benefits

• Improve Workflows and Productivity
  Bots tackle repetitive queries, easing agent burnout.
• Decrease Agents’ Workloads
  Handle ~30% of support volume, freeing teams for high-value work.
• Bots Run Your Website 24/7
  Nonstop operation cuts costs and keeps engagement alive.
• Become a Better Problem Solver
  Instant answers in seconds skyrocket user delight and retention.
• Automatically Qualify Leads
  Engage prospects live, gathering details conversationally.
• Increase Conversion Rates
  Leverage quick, pro responses to lift sales.
• Create Chatbots using Your Data
  Build ChatGPT-style bots from your files or site links. Amp up with Flows, Q&A, and Google AI.
  Auto-train from sites, sitemaps, PDFs, JSON, and docs.
  Schedule retraining via cron or API.

Major Settings & Configuration

Tailor these essentials to fit your ecommerce or support goals perfectly.

1. Training Data Input
   Fuel precision with varied inputs:
   • Files & Text: Load PDFs or plain text for your knowledge core.
   • URLs & Sitemaps: Scan live site pages (set HTML lang for multilingual sites).
   • Chat History: Refine with real past interactions.
     Path: Chatbot > Training. Fix issues: Info > Clear all data, then retrain.
2. Embedding Model
   OpenAI’s text-embedding-3-small turns text to vectors for deep semantic grasp.
   Cost: ~$0.00000004/token—prime performance-value mix.
3. Automation & Frequency
   Sync bots to fresh content via cron jobs or API for hands-free updates.
4. Fine-Tuning Parameters
   Shape tone in OpenAI Settings:
   • Temperature: Low (0.2) for precise support; high (0.8) for creative chats.
5. Language Detection
   Global-ready: Auto-spot user language, reply matchingly. Enable “Multilingual via translation” for KB and category auto-translations.
6. Quality Control Tools
   • Spelling Correction: Pre-process user typos for flawless understanding.
   • Rewrite Message: One-tap rephrase for clearer bot outputs.
7. Intent Detection Confidence
   Set threshold (rec: 0.81)—below it, fallback to default or human escalation to dodge errors.

Human Takeover

Humans stay in charge. Bot stumbles? Trigger handover with smart alerts—only when essential.

• Multiple human takeover methods
• Notifications only when needed
• User confirmations
• Other options

Multilingual Chatbots

One-click global switch: Detect language, translate live, respond natively (50+ tongues).

• Real-time message translation
• Language detection
• More than 50 languages
• Multilingual chatbots

Works with WhatsApp, Instagram and More

Link to top channels for unified reach.

• WhatsApp
• Instagram
• Telegram
• Messenger
• Viber
• More

Smart Questions and Answers

Build Q&A boosted by OpenAI, pulling live from APIs/external sources. Trigger saves/actions on key queries.

• Provide answers from external sources
• Actions on specific questions

Tools Calling

OpenAI tools grab/validate data (e.g., tracking codes) and fetch real-time info.

• Set Data: Snag emails, addresses, custom fields on triggers.
• Actions: Archive chats, email agents, force handover, etc.

Chatbot Flows

Design guided sequences: Collect info, list buttons, API calls, conditionals.

• Collect user details
• Send button lists
• Send data via REST API
• Set conditions
• Conversational Mode: AI reads messages, picks options naturally.
• Step-Back Updates: “Fix email” or “Back” revisits steps.
• Messaging Channels: Full WhatsApp/etc. compatibility.

Speech Recognition

OpenAI transcribes audio to text instantly—pairs with translations, works for all users/bots/admins.

Image and File Analysis

OpenAI Vision decodes images/files (PDFs, DOCX, TXT, GIFs, etc.) for sharper insights.

• Analyze multiple images and files at same time
• Supports PDF, DOCX, TXT, GIF, WEBP, PNG, JPG, and more formats

Chatbot Training on the Fly

Agents add Q&A live—OpenAI generates variants for robust learning (multilingual too).

• OpenAI enhancement
• Have your agents train the chatbot
• Multilingual training

Chatbot Actions

Bots act for users: Email sends, article opens, dept switches, handoffs (+10 actions in Flows/Q&A).

• More than 10 actions available
• Allow the chatbot to act on behalf of the user

Chatbot Live Web Search

Bot scours Google for fresh events/news, fixes typos too.

• The chatbot answers questions about real-time events
• Correct misspelled user questions

Rich Messages

Bot rivals humans: Attachments, media, 10+ rich types via shortcodes.

• Rich messages as shortcode
• Attachments and media
• 10+ rich message types

Chatbot Integrations

Level up with these:

Google Calendar
With the powerful Google Calendar integration, your chatbot can create and manage bookings automatically, while admins and agents easily view and control them from the panel.

TidyCal
With the powerful TidyCal integration, your chatbot can create and manage bookings automatically, while admins and agents easily view and control them from the panel.

Unlimited OpenAI Assistants

Deploy endless assistants, activate site-zone specifically.

Real-time Data

Bots tackle current events/news dynamically.

Message Rewriting & Smart Reply

AI polishes agent messages (friendlier, pro) or suggests quick hits based on context.

Automatic Training

Cron/API retrains on content/chats regularly.

Fine Tune OpenAI & Prompt Editing

Tweak temp, models, freq; customize prompts for vibe and key info.

Revolutionizing Customer & Lead Management with CHAT App

In today’s fast-paced digital landscape, the bridge between a potential lead and a confirmed appointment needs to be shorter than ever. The CHAT App ecosystem offers a comprehensive lead management and scheduling solution that integrates directly with your existing workflows via Google Calendar and TidyCal.

By combining AI-driven conversations with robust calendar synchronization, businesses can automate the most tedious parts of the sales funnel while maintaining a personal touch.

🚀 The Power of Integrated Lead Management

At its core, Lead Management in the CHAT App cloud version is designed to organize, track, and manage potential customer information in one centralized location.

• Manual & Bulk Entry: Add leads manually through the admin panel or import them using supported formats.
• Progress Tracking: Monitor every stage of the sales journey, from the initial contact to final conversion or disqualification.
• Smart Assignment: Ensure no lead is left behind by assigning them to specific agents or team members, either manually or through automated rules.
• Persistent Follow-ups: Boost conversion rates by setting automated reminders to ensure timely contact with every prospect.

📅 Seamless Calendar Synchronization

One of the standout features of the CHAT App is its ability to transform a simple chat interface into a powerful scheduling engine. By integrating Google Calendar or TidyCal, you unlock a suite of automated booking capabilities.

Intelligent AI Booking

The days of static forms are over. Leads can book appointments naturally through a conversation with the AI chatbot. The bot guides them through the process, understanding their needs and checking availability in real-time.

Complete Control & Customization

Admin users and agents have full visibility via a unified calendar dashboard.

• Real-Time Sync: Whether an appointment is created, updated, or canceled via the chatbot or the admin panel, it stays perfectly synchronized with your external calendars.
• Tailored Settings: Configure your office hours, available time slots, slot durations, and buffer times directly from the dashboard to ensure your schedule remains manageable.

Global & Multi-Channel Reach

The CHAT App is built for a global audience. The booking system is multilingual, allowing the chatbot to communicate in any language. Furthermore, these integrations work across a massive array of messaging platforms, including:

• WhatsApp, Messenger, and Instagram
• Telegram, Line, Viber, and Zalo
• Live chat, Email, and SMS

🛠️ Industry Use Cases: Scheduling in Action

The flexibility of the CHAT App makes it an ideal fit for a wide variety of professional sectors:

Other supported industries include legal services, fitness training, event planning, and hospitality.

❓ Frequently Asked Questions

How quickly can I set up the integration? Setup takes only a few minutes. Simply connect your Google Calendar or TidyCal account and configure your preferences in the CHAT App dashboard.

How does the system handle notifications? To reduce no-shows, the system automatically sends booking confirmations, reminders, and updates to both agents and customers via their preferred messaging platform.

What happens if appointments don’t sync correctly? First, ensure your integration is authorized in the dashboard. Real-time synchronization is designed for consistency, and quick setup guides are available to help troubleshoot any authorization issues.

Can the chatbot handle cancellations? Yes. The chatbot can create, update, and cancel bookings in real-time, ensuring your calendar always reflects the most current availability.

Turbocharge Customer Support & Efficiency with CHAT App Tools

Revolutionize Support for Ecommerce Lead Gen & Customer Service!
For ecommerce lead generation, streamline inquiries into qualified leads with smart routing, instant replies, and omnichannel capture—fueling sales pipelines effortlessly.
For customer support, slash response times, delight users with AI-powered tools, and unify all channels in one intuitive hub, turning support into a growth engine.

Boost Clients’ Support Efficiency with Our Tools

Handle every conversation and user from a central hub, ditching scattered tools forever. Now it’s just you and the customer—seamlessly linked via CHAT App. Dive in today?

Manage Conversations

Oversee all chats in a single, intuitive dashboard. Hunt down discussions, erase notes, track live user presence, and spot typing activity as it happens.

• Delete messages
• Download conversations
• Search for conversations
• Online and typing status

Knowledge Base Articles

Speed up resolutions and cut agent workload with a built-in, multi-language help hub. Whip up a dedicated resource zone or embed it in chats within moments.

• Dedicated articles page, demo here
• Search articles widget
• Categories
• Multilingual

Message Editor

Craft flawless replies using 3000+ emojis and markdown for sleek formatting. Delight users with voice clips, plus drag-and-drop media and files.

• Text formatting and markups
• 3000+ emojis
• Attachments
• Voice messages

Saved Replies

Slash repetition with pre-saved responses—no more retyping basics. Link them to the chatbot for on-demand auto-replies and dynamic queries.

• Insert by keyboard shortcut
• Save and reuse messages
• Connect to the chatbot to auto-generate responses

Departments

Sort chats and allocate teams to specialists. Set transfer logic so queries always reach the perfect handler. Dispatch department-tailored email alerts.

• Department email notifications
• Update conversations department
• Restrict access to conversations

Notifications

Keep engagement alive—never miss a beat with our full notification suite.

Email

Ping users and team via email on every incoming message.

Push Notifications

Notify users and team via push alerts for fresh messages.

Desktop Notifications

Trigger desktop pops for users and team on new messages.

SMS Notifications

Send text alerts to users and team for each new message.

Flash Notifications

Flash the browser tab title with every new arrival.

Sounds

Chime on every incoming message.

Red Counter

Show a red badge with unread message count.

Agents and admins

All notification types work in the admin zone too.

More are coming

Fresh notification options rolling out soon—watch this space!

Real-time Queue

Inform visitors of their queue spot and wait time live. Evenly spread chats across online agents and cap active sessions per person.

• Waiting time and queue position
• Set max concurrent chats limit
• Updates in real-time

Routing and Agent Assignment

Distribute chats fairly to free agents or let users pick favorites. Optimize flow and delight with clever assignment smarts.

• Auto-route chats to agents fairly
• Let your users select their preferred agent

Email Piping

Respond to emails from your inbox and morph them into chats. Customers reply via email too! Skip server tweaks—just add IMAP/POP3 credentials.

• Reply to users via email
• Users can reply by email
• No server-side configuration
• Multiple email accounts

Omni-Channel Experience

Unify WhatsApp, Facebook, Telegram, SMS, emails, tickets, and chats in CHAT App. Centralize comms to save hours.

• WhatsApp
• Messenger
• Telegram
• Slack
• Text Messages
• Emails

Translations in Real-Time

Chat fluidly in any language—auto-translate between user, agent, or bot for seamless global support.

• Two-way translations
• Translations in real-time
• Multilingual chatbot
• Powered by Google Translate

Smart Reply

AI crafts instant reply ideas for agents in real time, pulling from OpenAI and Dialogflow in the user’s tongue.

• OpenAI and Dialogflow suggestions
• Multilingual suggestions

Message Rewriting

One-click AI overhaul via OpenAI turns drafts into polished, friendly pros. Trigger on sentiment for perfect tone.

• Revitalize your messages with a friendly and professional touch
• Rewrite messages only when sentiment analysis triggers it

Spelling Correction

AI zaps typos in agent messages instantly, across languages—powered by OpenAI. Error-free chats, always.

• Fix any spelling mistakes
• Multilingual spelling correction

Smart Private Notes

Drop private notes on chats; AI auto-summarizes and pulls key info like links or contacts. Admin-eyes only.

• Automatically extract data such as URLs and private details
• Automatically generate conversation summaries using AI

Multi-User Direct Messaging

Beam real-time chats, emails, or SMS to users with personalized merge tags and auto-alerts.

• Support for emails, SMS and text messages
• Send messages to several users

Reports

Track chat performance and agent metrics at a glance.

• Daily conversations
• Missed conversations
• Average conversations time
• Registrations count
• Subscribe and follow-up reports
• Daily visitors
• Daily leads
• Daily users
• Articles searches and views
• Browsers and operating systems
• Agents ratings
• Agents response time
• Average agent conversations time
• Countries and languages
• More available and more are coming!

Agent Ratings

Capture post-chat feedback. Review scores per chat or agent, even gather via conversational AI on WhatsApp and beyond.

• View ratings by conversation and by agent
• Collect feedback conversationally on messaging channels

Tickets

Embed ticket zones site-wide for instant customer aid from one spot. Needs the Tickets app.

More details

Offline Message

Show custom banners or messages outside hours or when team’s away. Tailor timing, style, and triggers.

• Multiple message types and designs
• Display timetable
• Disable agents check

More Features

CHAT App packs powerhouse tools for any-scale operations.

• Transcript
  Grab chat logs as text files and share with users.
• Routing
  Fairly divvy chats among the team.
• Message Reply
  Quick one-tap responses, app-friendly.
• Tags
  Label and sort chats effortlessly.
• Agents Collision Detection
  Block duplicate agent handling.
• Automatic Updates
  One-click or auto plugin/app refreshes.
• Multilingual Platform
  41 languages built-in—add yours easily.
• Keyboard Shortcuts
  Boost speed with hotkeys.
• Attachments, Media and Lightbox
  Share files/media; preview pics in lightbox.
• Documentation
  Dive into full guides anytime.

Supercharge Leads, Sales & Support with AI Chat Power

Ecommerce Lead Gen & Customer Support Revolution!
For ecommerce stores, capture emails, nurture leads, and close sales faster with smart pop-ups, automated funnels, and seamless newsletter integrations—turning browsers into buyers.
For customer support, deliver instant human-like help, proactive outreach, and rich messaging to resolve issues on the spot, boost satisfaction, and build loyalty that drives repeat business and referrals.

Boost Marketing with AI Powered Tools and Chat

Live chat adds a personal touch and instant support, creating a standout marketing edge for lead capture and support excellence. Customers adore it with every use, driving up sales, generating hot leads, and sending revenues soaring while resolving queries effortlessly.

Pop-up Message

Show targeted pop-up messages on your site to grab ecommerce leads or offer instant support. Make them irresistible with compelling text and profile pictures. Build various pop-ups that trigger automatically for high-intent scenarios like cart abandonment or support needs.

• Multiple pop-ups
• Automated pop-ups
• Multilingual

Welcome Message

Greet ecommerce visitors or support seekers with a warm welcome the moment they land and open chat—perfect for lead gen intros or quick help offers. Trigger it on page load or chat open, and set up several via automations to personalize the experience.

• Multiple options
• Multiple and automated messages
• Multilingual

Follow-up message

In ecommerce, snag abandoned cart emails; in support, collect details if no agent’s available. Dispatch a message asking for the user’s email if no agent responds in 15 seconds—or when all agents are offline. It handles phone numbers and additional fields for richer lead data or tickets.

• Support for phone number and other fields
• Multilingual

Subscribe Message

Grow your ecommerce list or support community via live chat. Prompt users for their email and configure follow-up confirmation emails to nurture leads or send updates. It connects seamlessly with leading newsletter platforms for effortless growth.

• Integration with the major newsletter services
• Multilingual message and email

Newsletter Subscription

Push ecommerce leads down the funnel or keep support users engaged by auto-subscribing them to your newsletter when they share an email in chat. Pick a specific list, add their name, and watch conversions climb.

• Mailchimp
• Elastic Email
• Campaign Monitor
• Sendinblue
• SendGrid
• HubSpot
• Moosend
• GetResponse
• ConvertKit
• ActiveCampaign
• MailerLite
• Mailjet
• Sandy
• SendFox

Automations and Triggers

Automate lead gen for ecommerce (like exit-intent captures) and support workflows (like ticket escalations). Dispatch messages, display pop-ups, tweak chat designs, and more when your defined conditions are met. Tap into over 13 conditions and 5 automation varieties.

• Messages, pop-ups, emails, SMS, and design
• More than 13 conditions

Multi-Users Direct Message

Nurture ecommerce leads or follow up on support cases in real time. Deliver direct chat messages, emails, and SMS to users, tailored with custom merge fields and automatic notifications.

• Support for emails, SMS and text messages
• Send messages to several users

Marketing Chatbot

Pair with ecommerce for 24/7 lead qualification or support for instant query handling. Supercharge these tools by combining them with the chatbot—it automates replies to campaign questions or issues, enhancing experiences while saving time.

Explore our Smart Chatbot

Social Share

Amplify ecommerce traffic or support advocacy by encouraging shares. Message customers to share the current page on social platforms and apps like Facebook, Twitter, and others—boosting visibility and engagement.

• Support for Facebook, Twitter, Whatsapp, Linked-in, Pinterest
• More services coming soon

Proactive Chat

For ecommerce, spot shopping intent; for support, preempt issues. Let agents contact online visitors before they chat—from the admin panel, view the real-time user list and invite anyone to convert or get helped.

• Real-time online users list
• Send a message to online users

Rich Messages

Wow ecommerce shoppers with product previews or empower support with guides. Agents captivate users with over 10 types of rich messages, mixing them seamlessly. Insert via parameter strings or shortcodes.

• 10+ rich message types
• Custom rich messages
• Rich message as shortcode
• Multilingual

Booking System

Ecommerce sellers book demos; support teams schedule calls. Calendly integration makes booking meetings with visitors effortless—right from the chat widget or tickets section.

Powered by Calendly
Try it now by clicking here

Here is the full, SEO-optimized, and expanded article based on your documentation. I have utilized the specific GreenShift and WordPress blocks you provided to ensure a polished, “ready-to-paste” format.

The content has been slightly expanded for better flow and SEO context without altering the technical instructions.

Comprehensive Guide to Managing Conversations

Efficient conversation management is the backbone of excellent customer support. In this system, conversations are categorized into four distinct statuses to help you organize your workflow: mark as read, archive, delete, and restore. You can effortlessly manage the status of any active chat by opening it within the conversations area and selecting the corresponding icon located in the top-right corner of the window.

Advanced Search and Filtering

Finding specific interactions is straightforward with the robust search functionality. The system allows you to search using various data points to locate exactly what you need. If you search for specific message text, the system will not only find the conversation but also highlight the exact message string for quick reference.

• Department or Agent ID: Filter by specific internal IDs.
• User Details: Search by first name, last name, or email address.
• Content: Search by conversation title, message text, or attachment names.

Text Editor & Automated Message Features

The admin area text editor, used for live chats and automated messages (such as Welcome or Subscribe messages), supports robust styling options. This allows you to create stylized, professional, and clear communications.

Link Formatting: The system automatically converts text links into clickable hyperlinks. To customize the text of a link, append the following string to your URL: #sb-example. Simply replace “example” with your desired link name (use hyphens for spaces).

• Bold Text: Surround text with asterisks, e.g., *your text*.
• Italic Text: Surround text with double underscores, e.g., __your text__.
• Strikethrough: Surround text with tildes and colons, e.g., ~: ~your text~.
• Code Blocks: For single lines use backticks `code`. For blocks, use triple backticks ```block```.

Note: For security reasons, direct HTML, JavaScript, or other code languages are not permitted in the standard editor. However, you can achieve complex layouts using Rich Messages (detailed below).

Dynamic Merge Fields

Merge fields allow you to personalize automated messages by inserting dynamic variables that are replaced by external values when the message is sent.

Rich Messages & Interactivity

Rich messages transform standard text into interactive elements like buttons, sliders, dropdowns, and inputs. These are essential for creating engaging chatbots or collecting structured data from users. They are implemented using specific shortcodes.

Here is the corrected code block. I have restructured the “How Rich Messages Work” section to match the “Stack – Long steps” style you requested. The descriptive text has been moved from the heading subtitle into separate paragraph blocks below each step.

List of Rich Messages

[card image="URL" header="TITLE" description="Lorem ipsum" link="URL" link-text="Purchase" extra="$599" target="_blank"]

[slider image-1="URL" header-1="TITLE" description-1="Text" link-1="URL" link-text-1="Buy" image-2="URL"...]
[slider-images images="URL,URL,URL"]

[select options="Option A,Option B,Option C"]

[email name="true" last-name="true" phone="true" phone-required="false" placeholder=""]

Global Parameters: All rich messages support the following optional parameters to control behavior and data storage:

• Option id="123": The ID used to save the JSON data.
• Option title="ABC": The title displayed on the message.
• Option message="ABC": A description appearing underneath the title.
• Option success="ABC": The text shown after the user successfully completes the form.
• Option settings="ABC": Extra fields for optional values.

Integrations & Advanced Customization

Dialogflow Integration: To use rich messages within a Dialogflow chatbot, simply paste the desired shortcode directly into the “Text Response” field of the Intent.

Data Handling (JSON): When a user interacts with a rich message, the data is saved in the database under the `sb_messages` table in the `payload` column. The format is JSON:

{"rich-messages":{"UniqueID":{"type":"email","result":{"email":["[email protected]","User Input..."]}}}}

Custom HTML Codes: For advanced users, you can create custom rich messages via Settings > Miscellaneous. While these are static, you can use specific HTML classes for styling:

• Link with button design: Click here
• Zoomable Image:
  

System & Automated Messages

Admin Tools & Attachments

Attachments: The system automatically displays common image formats (.jpg, .png). To allow other file types (like .exe or .abc), you must modify the `config.php` file by defining the `SB_FILE_EXTENSIONS` array.

Tags & Notes: Administrators can assign tags to conversations for better filtering. Tags can also be assigned automatically via JavaScript variables (`SB_DEFAULT_TAGS`). Private notes can be added to conversations, visible only to agents and admins.

Knowledge Base & Ticket Management

Expand your customer support capabilities beyond real-time chat. This guide covers two essential modules: Articles and Tickets. Learn how to build a searchable Knowledge Base that reduces support volume and automatically trains your AI chatbot. Additionally, discover how to implement a structured Ticketing system for handling complex inquiries. Below, you will find installation steps, display methods (including WordPress shortcodes and script modifications), and advanced configuration options for both tools.

Articles (Help Center)
Empower your users to find instant answers and significantly reduce your support team’s workload. The Articles module allows you to create a fully integrated Knowledge Base that can be displayed directly in the chat dashboard, sent via rich messages, or hosted on a dedicated page. These articles also serve as a dynamic training source for your AI chatbot, ensuring your automated responses stay up-to-date.
Knowledge base articles provide instant answers to customers to help reduce customer support volume. You can access the articles from the left CHAT.devad.io menu.

• The articles can be shown in the chat dashboard by enabling them from Settings > Articles > Display in dashboard.
• Alternatively, articles can be shared in any chat conversation via the rich message shortcode, [articles].
• Follow these steps to display the articles on a page of your domain and website. You can display them in three ways:

The page shows the article categories, you must add parent categories and assign articles to them. The articles will be shown in the same location of the code above. You can hide the chat widget by adding the JS code var SB_DISABLED = true; to the page.

The article’s one-page navigation appears automatically on all articles. It is generated from the article’s h2 and h3 heading blocks.

To show Articles in your websites, use this code in your page. dont forget to add your API token which can be found in https://chat.devad.io/account/?tab=installation

<div id="sb-articles">
     <script src="https://chat.devad.io/script/js/min/jquery.min.js"></script>
     <script id="sbinit" src="https://chat.devad.io/script/js/main.js"></script>
     <?php
     $ch = curl_init('https://chat.devad.io/script/include/api.php?articles=true&' . (empty($_GET['category']) ? (empty($_GET['article_id']) ? (empty($_GET['search']) ? '' : '&search=' . urlencode($_GET['search'])) : '&article_id=' . $_GET['article_id']) : '&category=' . $_GET['category']) . (empty($_GET['lang']) ? '' : '&lang=' . $_GET['lang']));
     $parameters = [
         CURLOPT_RETURNTRANSFER => true,
         CURLOPT_SSL_VERIFYPEER => false,
         CURLOPT_USERAGENT => 'CHAT.devad.io',
         CURLOPT_POST => true,
         CURLOPT_CONNECTTIMEOUT => 5,
         CURLOPT_POSTFIELDS => http_build_query([
                                   'token'=> '[YOUR-TOKEN]',
                                   'function' => 'init-articles'
                               ])
     ];
     curl_setopt_array($ch, $parameters);
     $response = curl_exec($ch);
     curl_close($ch);
     echo $response;
     ?>
</div>

Another option is to install this javascript into a new page.
please note that to use the JS method you need to include the installation script code like <script id=”chat-init” src=”https://chat.devad.io/account/js/init.js?id=YOUR-CHAT-ID”></script> in your page where you want to display or use the chat. This script initializes the chat system on your site.

<script src="https://chat.devad.io/script/js/min/jquery.min.js"></script>
<script id="sbinit" src="https://chat.devad.io/script/js/main.js"></script>
<script>var SB_ARTICLES_PAGE = true;</script>
<div id="sb-articles" class="sb-loading"></div>

If you see 404 error, The 404 error on other pages when displaying articles means that the article categories or articles are not properly loaded or linked on those pages.
To fix this: Ensure the URL parameter for category or article_id is set correctly on those pages to load the right content.
Configure your website routes or permalinks so that requests for articles don’t lead to 404 errors.
Make sure parent categories and articles are assigned properly in the CHAT App admin area.
Optionally, use the REST API or PHP API method to load articles dynamically with proper parameter handling.
In brief, 404 means the pages are missing or not mapped properly to article content. You need to configure URLs and categories so that articles display correctly on all pages.

This training process enables you to train the chatbot using the articles.

• To train the chatbot add you articles and than click the Train chatbot button. The articles are used as training sources automatically.
• For more details click here.
• Articles All article languages are used automatically.
• CHAT.devad.io articles are synchronized automatically with the Dialogflow knowledge base.

When this option is active, the response will automatically include the links to the sources and training data used for generating the answer. To include articles as sources you have first to set the articles page in Settings > Articles > Articles page URL.

The system is extremely lightweight, built without frameworks or unnecessary code. It’s modular, minimal, and fully optimized for maximum performance.

Disable articles: Disable the articles area and article functionality. This reduces resource usage by preventing the system from loading articles on both the admin and client sides.

The Tickets app offers an alternative way for users to submit inquiries, providing a structured interface distinct from the standard chat widget. While it shares the same powerful backend as the chat system, the frontend is designed for creating and tracking longer-form requests. Whether you are using WordPress or a custom website, the guide below explains how to activate the app and display the ticket area using simple shortcodes or URL parameters.
The settings below are related to the Tickets app. The Tickets app allows users to create conversations and send messages via a UI different from the chat.

• From Settings > Apps, click Tickets and click Active.

WordPress

To display the tickets use the shortcode

[sb-tickets]

Insert it in any page, post, or post type item.

Any Website

To display the tickets area include the chat embed code into your page and add the attribute &mode=tickets to the script URL, e.g.

<script id="chat-init" src="https://chat.devad.io/account/js/init.js?id=YOUR-CHAT-ID&mode=tickets"></script>

. You can show the tickets area also by inserting the code

<script>SB_TICKETS = true;</script>

into any page showing the chat.

• If the tickets area is not visible, make sure to uncheck the option Tickets > Manual initialization. Additionally, you can explore other potential reasons for this issue here.
• You can also use the tickets area to display an inline or full-width chat panel.
• Tickets are the same of chat conversations on the admin-side, the only difference from chat conversations is the front-end UI.
• Most of the settings of the chat are compatible with the Tickets App but not all of them. The dashboard settings, the pop-up message, and more are not compatible.
• Dedicated APIs for the Tickets App are available in the API section.
• To remove the mandatory ‘New ticket’ form for new users, activate the welcome message of Settings > Messages & Forms > Welcome message. The welcome message delay is ignored in the tickets area, the message is sent immediately..
• To manually disable the mandatory registration only on a single page use the JavaScript code var SB_REGISTRATION_REQUIRED = true. Set it to true to force the registration instead.
• The tickets area is compatible with Google reCaptcha v3.

• CHAT.devad.io tries to process emails via cron jobs every 60 seconds, details here.
• If you’re using the cloud version the cron job is already activated by default and it will run at least once every 60 minutes.
• You can manually trigger execution and speed up cron jobs via API with the PHP function sb_email_piping(), or the WEB API function email-piping.
• You can create a cron job that runs the URL https://chat.devad.io/script/include/api.php?piping=true&cloud=API-TOKEN and replace API-TOKEN with your API token.
• If you manually run the cron job, activate the Disable cron job option to stop CHAT.devad.io from manually triggering it and to improve performance.

just enable the Settings > Artificial Intelligence > OpenAI > Training via cron job option and the cron job will be activated. You can disregard the instructions below.

To automatically train the chatbot with your website content at regular intervals, create a cron job that runs the URL https://chat.devad.io/include/api.php?open-ai-training=true, or use the command */59 * * * * wget https://chat.devad.io/include/api.php?open-ai-training=true to run it via a command. Replace https://chat.devad.io with your Installation URL, get it from Settings > Miscellaneous > Installation URL. use this URL: https://chat.devad.io/script/include/api.php?open-ai-training=true&cloud=API-TOKEN and replace API-TOKEN with your API token.

• the cron job can be executed at most once every 7 days.
• We strongly recommand providing an XML sitemap instead of the website URL for performance reasons.
• Automatic training is limited to websites; files, Q&A, and articles are excluded. Re-training will delete the previous website training data.

• Cron jobs are executed by the first user that visit the website at any given hour of the day.
• Cron jobs are executed every 60 minutes (60 seconds for email piping), but it can take longer, or it can take less time as well, in relation to the traffic of your website.
• Because cron jobs are initiated by users, if you have less than 1 visitor per hour (per minute for email piping), it could take longer. As long as there is at least one active user on the site, execution every 60 minutes (60 seconds for email piping) is guaranteed.
• You can speed up the cron jobs execution by manually run them via WEB API, or PHP API.

Automations allow running multilingual automatic tasks when conditions set by you are met.

• To delete a condition, set it to empty. To disable an automation, delete all conditions.
• Automations are sent only 1 time to users.
• If you used an automation in the past, and users already received it, you need to delete the automation and create a new one to show it to the users.
• Repeat only works if used in conjunction with date time.
• When date time is used in conjunction with the criteria is exactly, the value must not contain hours and minutes (hh:mm). Ex. 25/10/2021 (25/10/2021 10:30 will not work).
• The Settings > Users > Register all visitors option must be active if there are message automations that are executed on page load.
• City, countries, languages work automatically only if both the settings Settings > Users > Register all visitors and Settings > Users > Full visitor details are enabled.
• Cities work only if the user detail location is set and equal to city, country, or if the user detail city is set.
• Countries work only if the user details country_code, or country is set, or if the user detail location is set and equal to city, country. The country name must be in english.
• languages work only if the user details browser_language, or language is set.
• A visitor is a Returning visitor only if it visits the website again after 24h or more.
• The pop-ups appear only if the chat is closed, and they overwrite the default pop-up. You can check the message fallback option to send a message instead of showing the pop-up if the chat is open.
• You may need to enable Settings > Users > Register all visitors if you want to send an automated message to new users.
• Chat messages and popup fallback messages are sent only if the last user or agent message of the conversation is older than 10 minutes. This feature prevents unwanted automated messages to be sent during an agent-user conversation.
• The Custom variable condition check for the JavaScript variables with the given names and values. For example, the condition example=ABC is met if into the chat’s page there is this JavaScript code: var example = “ABC”;. Add multiple variables separated by commas.
• Automations are not compatible with the messaging apps like WhatsApp, Messenger, Instagram, Telegram, Twitter, Zalo, WeChat, Viber, Line.

Department Settings & Configuration

Organizing your support team into departments ensures that user inquiries are handled by the right experts. You can configure department behavior under Settings > Miscellaneous.

• Display in dashboard: Shows the department list in the chat dashboard, forcing users to select a department before starting a conversation.
• Display images: Shows the department image instead of the default department color.
• One conversation per department: Restricts users to one active conversation per department at a time.
• Labels: You can rename the default “Department” and “Departments” labels to suit your business needs (e.g., “Teams” or “Groups”).

How to Assign a Department

Departments can be assigned to a conversation automatically or manually via:

• Q&A Set Data: Configure your chatbot to assign departments based on user answers.
• Flow Actions: Use the flow builder to trigger assignment.
• Code: Use the JavaScript variable var SB_DEFAULT_DEPARTMENT = ID; on specific pages.
• Dashboard Selection: Force the user to choose from a list before chatting.

Smart Queue & Routing

When enabled, the system automatically distributes user conversations among available (online) agents proportionately. Admins are excluded from automatic assignment.

Email Piping Integration

Email piping allows you to sync email addresses so messages sent to your support email appear directly in the chat dashboard. Agents can reply from the dashboard, and users receive the reply via email.

• Delimiter: Use the delimiter option (### Please type your reply above this line ###) to cut out quoted replies and prevent duplicate message content.
• Attachments: Full support for email attachments.
• Reply-To: If the email contains a reply-to attribute, it serves as the primary user address.

System Optimization: Pusher & Cron

Cron Jobs

Cron jobs process emails and other scheduled tasks. While the cloud version runs this automatically every 60 minutes, you can trigger it manually every minute for faster email processing.

*/59 * * * * wget /include/api.php?piping=true

Pusher (WebSockets)

Activate Pusher to replace HTTP AJAX requests with WebSockets. This drastically improves performance, server load, and real-time responsiveness (typing status, online status, message delivery).

Direct Messages & Automations

Direct Messages: Send single messages via Chat, Email, SMS, or WhatsApp to individual or all users.
Automations: Run multilingual automatic tasks when specific conditions are met (e.g., “User visits pricing page” -> “Send discount code”).

• Conditions: Set criteria like city, country (English name), language, or custom variables.
• Restrictions: Automations run once per user. They are not compatible with external messaging apps (WhatsApp, Messenger).

Newsletter Integrations

Synchronize user emails collected via registration forms or follow-ups with your preferred marketing platform.

Amazon S3 Attachment Storage

Saved Replies (Canned Responses)

Speed up agent workflow with pre-written messages. Manage them at Settings > Admin > Saved replies. Agents can quickly insert them by typing # followed by the reply name, or ## to open the full list.

Tickets Management System

The Tickets App provides a structured alternative to the real-time chat widget. It allows users to create conversations, track status, and send messages through a dedicated user interface, functioning similarly to a traditional support desk portal. This is ideal for managing inquiries that do not require immediate, real-time responses.

Installation & Activation

To enable this functionality, navigate to Settings > Apps in your dashboard. Select Tickets from the list and enter your license key to install and activate the module. If you are operating on the Cloud Version, simply click the Active button to enable the feature immediately.

Displaying the Tickets Interface

Depending on your installation type (WordPress, PHP, or Cloud), there are specific methods to render the tickets area on your website. Choose your platform below for instructions.

[sb-tickets]

Notifications Management Overview

Understanding exactly when and how notifications are triggered is essential for maintaining smooth communication. If you suspect notifications aren’t functioning correctly, please review the logic below, as testing methods often differ from real-world usage scenarios.

Email Notifications System

Both support agents and end-users can receive email alerts whenever a new message lands in their inbox. This ensures that no critical communication is missed, even when users are offline.

For Admins and Agents

When a user sends their very first message, the system intelligently routes the notification based on assignment rules:

• Department Assignment: If the chat is routed to a specific department, only agents within that department receive the email.
• Specific Agent Assignment: If assigned to a particular individual, only that agent is notified.
• Unassigned: If neither applies, an email is broadcast to all agents who are currently offline.

For subsequent messages in an ongoing conversation, emails are sent exclusively to the last agent handling the chat, provided they are currently offline. If the Human Takeover feature is active within the Artificial Intelligence app, the system suppresses notifications if the chatbot successfully answers the query.

For Users

Users receive email notifications only when an agent replies and the user is currently offline. To prevent inbox spam, only one email alert is sent per offline session; subsequent messages will not trigger additional alerts until the user returns.

Customizing Email Templates

You can fully customize the content of these emails via Settings > Notifications. The editor supports both plain text and HTML. New lines are automatically converted to HTML line breaks. Use the following dynamic merge fields to personalize your messages:

Optimization via Cron Jobs

For a more robust notification system, you can offload email sending to a cron job. This is highly recommended as it improves performance and ensures emails include the entire conversation context.

Use the following command format, replacing [SCRIPT-URL] with your actual Installation URL found in Settings > Miscellaneous:

*/59 * * * * wget [SCRIPT-URL]/include/api.php?email-notifications=true

Troubleshooting Email Delivery

Real-Time Push Notifications

Unlike standard desktop notifications, Push notifications are delivered from a server even when the user’s browser is closed or the device is offline. We support both Pusher (Android/Desktop) and OneSignal (iOS/Android/Desktop). Note that iOS devices strictly require OneSignal.

Setup: OneSignal (iOS Support)

For Apple devices (iOS 16.4+), you must use OneSignal. The setup involves creating a Web Configuration in OneSignal, entering your site’s root domain, and uploading the required SDK files (sw.js etc.) to your server’s root directory.

• Cloud Version: OneSignal is pre-configured by default.
• WordPress: You must access the chat admin area directly (outside the WP dashboard) to finalize push settings.
• Service Workers: You need to define the path to your service worker files in the settings if they are not in the root.

Additional Notification Types

Desktop Notifications

These are standard browser notifications. They work only over HTTPS and are not supported on iOS. If Push notifications are active, they will override and replace standard desktop notifications.

SMS Notifications (Twilio)

You can send SMS alerts to both agents and users via Twilio integration. This also enables a true two-way texting experience where SMS replies appear in the chat.

• Setup: Enter your Twilio SID, Auth Token, and Phone Number in Settings > Notifications > Text message notifications.
• Sender ID: You can replace the phone number with a custom Sender Name (Alphanumeric Sender ID) where supported.
• Logic: SMS notifications are sent only if the recipient is offline. They are disabled if the AI chatbot successfully handles the query.

Sound Alerts

Audio alerts play when a new message arrives. Due to browser security policies, sound will only play if the user has interacted with the document (clicked somewhere on the page). If set to loop, the sound plays until the chat window is opened or maximized.

Here is the full, SEO-optimized, and expanded article based on your documentation. I have utilized the specific GreenShift and WordPress blocks you provided to ensure a polished, “ready-to-paste” format.

The content has been slightly expanded for better flow and SEO context without altering the technical instructions.

Comprehensive Guide to Managing Conversations

Efficient conversation management is the backbone of excellent customer support. In this system, conversations are categorized into four distinct statuses to help you organize your workflow: mark as read, archive, delete, and restore. You can effortlessly manage the status of any active chat by opening it within the conversations area and selecting the corresponding icon located in the top-right corner of the window.

Advanced Search and Filtering

Finding specific interactions is straightforward with the robust search functionality. The system allows you to search using various data points to locate exactly what you need. If you search for specific message text, the system will not only find the conversation but also highlight the exact message string for quick reference.

• Department or Agent ID: Filter by specific internal IDs.
• User Details: Search by first name, last name, or email address.
• Content: Search by conversation title, message text, or attachment names.

Text Editor & Automated Message Features

The admin area text editor, used for live chats and automated messages (such as Welcome or Subscribe messages), supports robust styling options. This allows you to create stylized, professional, and clear communications.

Link Formatting: The system automatically converts text links into clickable hyperlinks. To customize the text of a link, append the following string to your URL: #sb-example. Simply replace “example” with your desired link name (use hyphens for spaces).

• Bold Text: Surround text with asterisks, e.g., *your text*.
• Italic Text: Surround text with double underscores, e.g., __your text__.
• Strikethrough: Surround text with tildes and colons, e.g., ~: ~your text~.
• Code Blocks: For single lines use backticks `code`. For blocks, use triple backticks ```block```.

Note: For security reasons, direct HTML, JavaScript, or other code languages are not permitted in the standard editor. However, you can achieve complex layouts using Rich Messages (detailed below).

Dynamic Merge Fields

Merge fields allow you to personalize automated messages by inserting dynamic variables that are replaced by external values when the message is sent.

Rich Messages & Interactivity

Rich messages transform standard text into interactive elements like buttons, sliders, dropdowns, and inputs. These are essential for creating engaging chatbots or collecting structured data from users. They are implemented using specific shortcodes.

Here is the corrected code block. I have restructured the “How Rich Messages Work” section to match the “Stack – Long steps” style you requested. The descriptive text has been moved from the heading subtitle into separate paragraph blocks below each step.

List of Rich Messages

[card image="URL" header="TITLE" description="Lorem ipsum" link="URL" link-text="Purchase" extra="$599" target="_blank"]

[slider image-1="URL" header-1="TITLE" description-1="Text" link-1="URL" link-text-1="Buy" image-2="URL"...]
[slider-images images="URL,URL,URL"]

[select options="Option A,Option B,Option C"]

[email name="true" last-name="true" phone="true" phone-required="false" placeholder=""]

Global Parameters: All rich messages support the following optional parameters to control behavior and data storage:

• Option id="123": The ID used to save the JSON data.
• Option title="ABC": The title displayed on the message.
• Option message="ABC": A description appearing underneath the title.
• Option success="ABC": The text shown after the user successfully completes the form.
• Option settings="ABC": Extra fields for optional values.

Integrations & Advanced Customization

Dialogflow Integration: To use rich messages within a Dialogflow chatbot, simply paste the desired shortcode directly into the “Text Response” field of the Intent.

Data Handling (JSON): When a user interacts with a rich message, the data is saved in the database under the `sb_messages` table in the `payload` column. The format is JSON:

{"rich-messages":{"UniqueID":{"type":"email","result":{"email":["[email protected]","User Input..."]}}}}

Custom HTML Codes: For advanced users, you can create custom rich messages via Settings > Miscellaneous. While these are static, you can use specific HTML classes for styling:

• Link with button design: <a href="..." class="sb-rich-btn sb-btn">Click here</a>
• Zoomable Image: <div class="sb-image"><img src="..." class="sb-image" /></div>

System & Automated Messages

Admin Tools & Attachments

Attachments: The system automatically displays common image formats (.jpg, .png). To allow other file types (like .exe or .abc), you must modify the `config.php` file by defining the `SB_FILE_EXTENSIONS` array.

Tags & Notes: Administrators can assign tags to conversations for better filtering. Tags can also be assigned automatically via JavaScript variables (`SB_DEFAULT_TAGS`). Private notes can be added to conversations, visible only to agents and admins.

Department Settings & Configuration

Organizing your support team into departments ensures that user inquiries are handled by the right experts. You can configure department behavior under Settings > Miscellaneous.

• Display in dashboard: Shows the department list in the chat dashboard, forcing users to select a department before starting a conversation.
• Display images: Shows the department image instead of the default department color.
• One conversation per department: Restricts users to one active conversation per department at a time.
• Labels: You can rename the default “Department” and “Departments” labels to suit your business needs (e.g., “Teams” or “Groups”).

How to Assign a Department

Departments can be assigned to a conversation automatically or manually via:

• Q&A Set Data: Configure your chatbot to assign departments based on user answers.
• Flow Actions: Use the flow builder to trigger assignment.
• Code: Use the JavaScript variable var SB_DEFAULT_DEPARTMENT = ID; on specific pages.
• Dashboard Selection: Force the user to choose from a list before chatting.

Smart Queue & Routing

When enabled, the system automatically distributes user conversations among available (online) agents proportionately. Admins are excluded from automatic assignment.

Email Piping Integration

Email piping allows you to sync email addresses so messages sent to your support email appear directly in the chat dashboard. Agents can reply from the dashboard, and users receive the reply via email.

• Delimiter: Use the delimiter option (### Please type your reply above this line ###) to cut out quoted replies and prevent duplicate message content.
• Attachments: Full support for email attachments.
• Reply-To: If the email contains a reply-to attribute, it serves as the primary user address.

System Optimization: Pusher & Cron

Cron Jobs

Cron jobs process emails and other scheduled tasks. While the cloud version runs this automatically every 60 minutes, you can trigger it manually every minute for faster email processing.

*/59 * * * * wget /include/api.php?piping=true

Pusher (WebSockets)

Activate Pusher to replace HTTP AJAX requests with WebSockets. This drastically improves performance, server load, and real-time responsiveness (typing status, online status, message delivery).

Direct Messages & Automations

Direct Messages: Send single messages via Chat, Email, SMS, or WhatsApp to individual or all users.
Automations: Run multilingual automatic tasks when specific conditions are met (e.g., “User visits pricing page” -> “Send discount code”).

• Conditions: Set criteria like city, country (English name), language, or custom variables.
• Restrictions: Automations run once per user. They are not compatible with external messaging apps (WhatsApp, Messenger).

Newsletter Integrations

Synchronize user emails collected via registration forms or follow-ups with your preferred marketing platform.

Amazon S3 Attachment Storage

Saved Replies (Canned Responses)

Speed up agent workflow with pre-written messages. Manage them at Settings > Admin > Saved replies. Agents can quickly insert them by typing # followed by the reply name, or ## to open the full list.

Tickets Management System

The Tickets App provides a structured alternative to the real-time chat widget. It allows users to create conversations, track status, and send messages through a dedicated user interface, functioning similarly to a traditional support desk portal. This is ideal for managing inquiries that do not require immediate, real-time responses.

Installation & Activation

To enable this functionality, navigate to Settings > Apps in your dashboard. Select Tickets from the list and enter your license key to install and activate the module. If you are operating on the Cloud Version, simply click the Active button to enable the feature immediately.

Displaying the Tickets Interface

Depending on your installation type (WordPress, PHP, or Cloud), there are specific methods to render the tickets area on your website. Choose your platform below for instructions.

[sb-tickets]

<script id="chat-init" src="https://chat.devad.io/account/js/init.js?id=YOUR-CHAT-ID&mode=tickets"></script>

<script>SB_TICKETS = true;</script>

Team Workflow & Conversation Routing Settings

Scale your support operations with powerful distribution and organization tools.

• Departments: Segment your team (e.g., Sales, Support) and route conversations accordingly.
• Queue & Routing: Automatically distribute incoming chats to available agents or place users in a waiting line when demand is high.
• Email Piping: Seamlessly integrate your email inbox, allowing agents and users to reply to chat messages directly from their email clients.
• Office Hours: Define your team’s availability to trigger offline messages or hide the chat widget outside of business hours.

Departments give you the power to distribute conversations and assign various agents to specific departments. For example, you can create a department entitled “Sales” and assign specific conversations to that department. To start using departments, follow the steps below:

• Go to Settings > Miscellaneous and add, delete and manage the departments. After saving, reload the page.
• Go to Users > Agents and edit an agent, you will see a new field where you can set the department of the agent.
• Reload the page and you’re done! In the Conversations area, you will now see an option to set the department.

• Display in dashboard Displays the departments’ list in the chat dashboard and force users to choose a department before starting a conversation.
• Display images Displays the department image instead of the department color.
• Display in conversation list Displays the department color in the conversation list of the admin area.
• One conversation per department Restrict users from opening multiple conversations within the same department, allowing only one conversation to be active per department.
• Label Replace the label Departments (plural) with another text. The name is displayed in the admin and tickets area.
• Label single Replace the label Department (singular) with another text. The name is displayed in the admin and tickets area.
• Dashboard title Set the title of the chat dashboard list. Default: Departments.

• Agents and admins with no assigned department always see the conversations of all departments.
• Agents and admins with an assigned department can only access conversations, users, and agents within that department.
• When a conversation is assigned to a new department, an email notification is sent to all of the agents assigned to the new department.
• The chatbot can assign a department to the active conversation through the Q&A set data feature, the flows actions feature, or Dialogflow actions.

You can assign a department to a conversation in several ways:

• Via the Q&A set data feature.
• Via the flows actions feature.
• Via Settings > Miscellaneous > Departments settings > Display in dashboard. In this case, the user will be required to select a department before starting a new conversation.
• Via Settings > Automations > More.
• Via JavaScript, with the variable var SB_DEFAULT_DEPARTMENT = ID;. Enter the code into the pages where the chat is displayed and replace ID with the department ID. For more details check the API here.
• Via API.

If the Settngs > Slack > Department linking option is active, when a conversation in the CHAT.devad.io is assigned to a department, a new message is sent to the linked Slack channel, informing Slack users that a new conversation has started and inviting them to join the dedicated user Slack channel. However, the full conversation can only be accessed on the dedicated Slack channel of the specific user.

• Get the department IDs from Settings > Miscellaneous > departments.
• Get the channel IDs by clicking the button Get channel IDs.

When the queue is activated via Settings > Miscellaneous > Queue, or routing is activated via Settings > Miscellaneous > Routing, CHAT.devad.io automatically assigns the users conversations to all available agents proportionately.

• Only online agents are counted as “available” agents and will receive new conversations. Conversations are assigned proportionally between all online agents. If no agents are online, the conversation will remain unassigned and will be automatically assigned to the first agent who comes online.
• Admins are not included; admins always see all the conversations.
• Agents must archive a conversation to mark it as completed; this will automatically give them access to the next conversation in the queue. A conversation is active if it’s not deleted, or archived.
• Agents can switch their status between online and offline by hovering over their profile image and then clicking the label of the profile pop-up at the bottom-left of the admin area.
• Agents can only search and filter their conversations.
• Agents can only view their conversations; however, they can see all of the conversations of a single user.
• To enable agents to view all unassigned conversations, activate Settings > Miscellaneous > Hide conversations of other agents and View unassigned conversations.
• Queue and routing are compatible with the departments.
• If human takeover is active, the queue or routing is activated only on human takeover.
• When routing or queue is active, the agents menu will be automatically enabled.

When the queue is activated users enter into a queue automatically when an agent’s chat limit is reached. When a user enters the queue, a message with the current position in the queue and the estimated waiting time is displayed. CHAT.devad.io automatically assigns the conversations to all available agents proportionately. When an agent marks a conversation as completed (by archiving it), the queue is updated and a new conversation is received.

• If a user is in the queue and leaves (e.g. by closing the browser) for more than 1 minute, the conversation is saved; however, once the user comes back, the queue is reset and the user will lose their previous position. If the user leaves, the conversation remains unassigned and therefore invisible to agents, but only visible to admins.
• You can use the following merge fields in the queue message: {position}, {minutes}. They will be replaced by the real values in real-time.
• The waiting time is displayed in minutes and is calculated as follows: queue position X response time = waiting time. For example, if a user is 5th in the queue, and the response time has been set to 4 minutes (via Settings > Miscellaneous > Queue), then the total wait time displayed to the user will be 20 minutes.
• When the sound option is active, a sound is played when it’s the user’s turn.
• For conversations started from messaging apps like WhatsApp, it is not possible to respect the limit of conversations per agent, all conversations will be immediately and proportionally assigned to an online agent. If no agents are online, the conversation will remain unassigned and will be automatically assigned to the first agent who comes online.
• Use the offline message to prevent the chat from showing the queue update message to the user.

To test the queue, follow the steps below:

• To simulate multiple users and agents, open the chat in multiple different browsers (e.g. Opera, Firefox, Brave, Chrome, etc.). Each browser can simulate two users/agents: one in normal mode and one in “private” or “incognito” mode.
• To reset the chat and start a new user session, open the browser console, enter SBF.reset(), and press ENTER.

When the routing is activated CHAT.devad.io automatically assigns the users conversations to all available agents proportionately.

• If the Routing > Disable online status check option is active, the conversations are distributed proportionally among all agents, regardless of whether they are online or offline.
• When an agent comes back online after being offline, all unassigned conversations are automatically assigned to them.
• When routing is active agents can manually route conversations to other agents from the right panel of the conversations area.
• If the conversation is archived and the user reopens it in the future by sending a new message, if the assigned agent in the conversation is offline, the conversation is assigned to another agent.

When the routing is activated via Settings > Miscellaneous > Hide conversation of other agents agents see only their own conversations and can select the unassigned ones.

• Agents menu: enable the agents menu.
• Routing if offline: if the conversation is archived and the user reopens it in the future by sending a new message, if the assigned agent in the conversation is offline, the conversation is assigned to another online if there is at least one, otherwise to no agent.
• View unassigned conversations: allow agents to view the unassigned conversations, when an agent replies the conversation is automatically assigned to him and the conversation is removed in real-time from the admin area of the other agents. Check this option to enable the manual routing.

The Agents menu lets you assign conversations to specific agents. It appears on the right side of the conversations area and is automatically enabled when queueing or routing is active. Select multiple conversations (see keyboard shortcuts) to assign the selected conversations to a specific agent.

You can assign an agent to a conversation in several ways:

• Via the Q&A set data feature.
• Via the flows actions feature.
• Via the queue or routing features.
• By enabling the Settings > Chat > Agents menu option. In this case, the user will be required to select an agent before starting a new conversation.
• Via Settings > Automations > More.
• Via JavaScript, with the variable var SB_DEFAULT_AGENT = ID;. Enter the code into the pages where the chat is displayed and replace ID with the agent ID. For more details check the API here.
• Via API.

Email piping lets you sync multiple email addresses to receive messages directly in CHAT.devad.io. It also allows you, your agents, and users to reply to chat messages via email.

• Go to Settings > Notifications > Email piping and enter your POP3/IMAP email server information.
• Go to Settings > Notifications > SMTP and enter your SMTP email server information. The email address must be the one to which the email piping server connects to. CHAT.devad.io will send all emails from this email address and you, your agents, and your users will reply to this email address. For more details check the email notifications section.

• The email address of Settings > Notifications > SMTP > Sender email should match the one used by the email piping server. If the email address does not match, or if multiple email addresses are configured for email piping, and the Username setting is defined as an email address, CHAT.devad.io will automatically include a reply-to field in the email notification. This ensures that when the user replies, their response is directed to the correct email piping address, keeping the conversation linked properly.
• The Notifications > User email notifications and Notifications > Agent email notifications settings are enabled automatically when email piping is active. When agents reply in CHAT.devad.io, emails are always sent to the user.
• If you’re using the Artificial Intelligence app, and the human takeover feature is activated, no emails are sent if the chatbot knows the answer.
• If the Convert all emails option is active:

You can set the office hours timetable from Settings > Miscellaneous > Office hours. Office hours are used for:

• Sending the offline message.
• Disabling and hiding the chat during out-of-office hours.
• Disabling the chatbot during regular office hours and enabling it during out-of-office hours.

• If a day has only one start and end time, enter them in the first two fields. For example, use 10:00 AM to 5:00 PM and (empty) to (empty), not 10:00 AM to (empty) and (empty) to 5:00 PM.
• Do not leave empty values. Set them to closed instead.
• You have to set values to closed if you want to set a whole day as not office hours.
• The office hours are in UTC format. Set your UTC from Settings > Miscellaneous > Timezone.
• The date and time format of the timetable matchs automatically the one used in the country of the browser language of the user.

Integrations, Tools, and Notifications
Guide to syncing newsletters, optimizing chat performance, and configuring email, push, and SMS alerts.

Follow the steps below to complete the synchronization with your newsletter service. The user is subscribed in the following cases: registration form, follow-up message, subscribe message, email shortcode.

• To get the Key, follow the docs at https://mailchimp.com/help/about-api-keys/.
• To get the List ID, follow the docs at https://mailchimp.com/help/find-audience-id/.

• To get the Key, go to https://account.brevo.com/advanced/api.
• To get the List ID, go to https://my.brevo.com/lists.

• To get the Key, go to https://app.sendgrid.com/settings/api_keys.
• To get the List ID, enter in SendGrid and click Marketing > Contacts(https://mc.sendgrid.com/contacts), then click on a list, or create a new one. The last part of the URL is the list ID. Ex. https://mc.sendgrid.com/contacts/lists/8558c1e7-3c99-4428-a68f-78df2e437f8e (the list ID is 8558c1e7-3c99-4428-a68f-78df2e437f8e).

• To get the Key, enter in Elastic Email, then click Settings from the top right profile menu. Click Create Additional API key (https://elasticemail.com/account#/settings/new/create-api), set a name and choose Plugin or Full access, or Custom and make sure the permission Contacts is set to View & Modify.
• The List ID is the list name. Important! Existing list’s or segment names must not have any spaces in them.

• To get the Key, enter in Campaign Monitor, then click Account settings from the top right profile menu. Click API keys > Generate API key.
• To get the List ID, enter in Campaign Monitor, then click List and subscribers from the top menu. Select a list and then click Settings from the left menu and copy the List API ID.

• To get the Key, enter in HubSpot, then get go to Settings > Integrations > Private apps and create a new app.
• Enter app name, then open the Scope tab and add the following scopes: crm.lists.write, crm.lists.read, crm.objects.contacts.read, crm.objects.contacts.write.
• Click Create app and copy the token. Paste the token into the Key field of CHAT.devad.io.
• To get the List ID, enter in HubSpot, then get it from Contacts > List > List details.

• To get the Key, enter in Moosend, then click Settings > API key.
• To get the List ID, enter in Moosend, then get it from Audience > Email lists.

• To get the List ID, enter in GetResponse, then get it from Lists > Your list > Settings(https://app.getresponse.com/lists). Copy the List token value.
• To get the Key visit https://app.getresponse.com/api.

• To get the Key, enter in ConvertKit, then get it from Settings > Advanced > API secret.
• To get the List ID, enter in ConvertKit, then get it from Grow > Landing Pages & Forms. Open you form and copy the numeric part of the URL. For example the ID of the form with URL https://app.convertkit.com/forms/designers/3003412/edit is 3003412.

• To get the Key, enter in ActiveCampaign, then get it from Account settings > Developer.
• To get the List ID, enter in ActiveCampaign, then get it from Left menu > Lists or Left menu > Contacts > Lists. Open your list and copy the list ID in the URL. For example the ID of the list with URL

• To get the Key, enter in MailerLite, then get it from Left menu > Integrations > MailerLite API.
• To get the List ID, enter in MailerLite, then get it from Left menu > Subscribers > Groups. View a group and copy the Group ID from the URL (e.g. ….group=18783408688903967…).

• To get the Key, visit https://app.mailjet.com/account/apikeys, or enter in Mailjet, then get it from Account settings > Account settings.
• To get the List ID, enter in MailerLite, then get it from Contacts > Contacts lists > Your list. Get the List ID by clicking the ? icon next to the lists’s email, e.g. 1202546.

• To get the Key, enter the Sendy settings area and copy the API KEY.
• To get the List ID, enter your brand, then click View all lists and copy the list ID. The list ID setting must also include your Sendy full URL. Enter the URL plus the list ID spearated by the char |, e.g. https://example.com|TDf6o892Mx11VXGC51ui567u.

• To get the Key, enter in SendFox, then get it from Settings > API > Personal Access Tokens.
• To get the List ID, enter in SendFox, then get it from Audience > Lists. Open a list and copy the ID from the URL (e.g. the List ID of the URL https://sendfox.com/dashboard/lists/489151/contacts is 489151).

• Log in to AWS as the root user from https://aws.amazon.com/.
• Enter the IAM dashboard and click Left menu > Access management > Users.
• Click Add new user, enter the username and continue.
• Select Add user to group and on the User groups section below click Create group. In Permissions policies search for AmazonS3FullAccess and select it. Click Create user group.
• Assign the new group to the user you are creating and continue, then click Create user.
• Select the newly created user and open the Security credentials tab.
• In the Access keys area, click Create access key and select Application running outside AWS. Continue until you get the keys and save them in CHAT.devad.io > Settings > Miscellaneous > Amazon S3.
• Visit the Amazon S3 dashboard and click Create bucket.
• Set the bucket name and region you want. Save the region and name in CHAT.devad.io > Settings > Miscellaneous > Amazon S3. Check ACLs enabled and Bucket owner preferred. Uncheck Block all public access and all related checkboxes.
• Click Create bucket.
• This feature is technical and optional. Support does not cover any help related to this feature.
• Be aware that it may take up to 24 hours for a newly created bucket to become active. If you have recently created an S3 bucket and it is not working, wait for 24 hours and try again.

Saved replies, also known as canned messages, refer to a collection of pre-written messages that agents can quickly access and employ in the chat editor. Manage them from Settings > Admin > Saved replies.

• Saved replies can be printed by typing # followed by the saved reply name, plus a space.
• The saved replies pop-up can be opened by typing ##.
• Use n to do a line break.
• If you are using the Dialogflow chatbot, the saved replies panel search will include results from Dialogflow Intents.
• You have the option to add all Dialogflow Intents to the saved replies list by using the option at Settings > Artificial Intelligence > Google > Add Intents to saved replies.

Activate Pusher from Settings > Miscellaneous > Pusher to use the WebSockets instead of HTTP AJAX requests for the chat functionalities. WebSockets drastically improve the chat performance by removing the need for repeated AJAX requests to your server for checking for new messages and conversations. WebSockets also improve responsivness of the chat: faster messages delivery, more accurate online and typing status, more accurate online users list and more. If you are using the cloud version, this setting is automatically activated.

• Go to https://dashboard.pusher.com/accounts/sign_up and create a new account.
• From your dashboard at https://dashboard.pusher.com, choose the Channels product by clicking Get started.
• Enter the name of your app and choose the cluster closest to your location.
• From the left menu of the dashboard click App Settings and enable client events.
• From the left menu of the dashboard click Keys, copy App ID, Key, Secret, Cluster.
• Go to Settings > Miscellaneous > Pusher, and paste app ID, key, secret, cluster.
• You’re done.

• Pusher is free to use for up to 200k messages and 100 concurrent connections per day. Messages are used for the following functions and more: user registration, online user status, chat messages, and chatbot messages. Pusher channels count calculation is explained here.
• When Pusher is active the following AJAX requests are replaced by WebSockets: checking for new messages, checking for new conversations, online/offline status, typing status, online users list.
• When Pusher is active the last activity value of users and agents is updated only on page load or when they send new messages.
• When Pusher is active the option Settings > Users > Register all visitors is automatically activated and it can not be disabled.
• If your server becomes overloaded, crashes, experiences excessive RAM usage, high CPU usage, or in general, slows down or has performance issues, activate Pusher.

Direct messages allow you to send а single chat message, email, or text message, to a single user or several users. Read the information below to understand how it works.

• To send a message go to the Users area and click the direct message icon. Direct message buttons are also available in the profile box of the user.
• To send a message to all users, enter All in the User IDs field.
• To send a message to a group of users, enter their IDs in the User IDs field. You can check the users and then click the direct message icon to enter the IDs automatically.
• All message types support merge fields.
• All message types support automatic translation.

• The chat message is sent to the active conversation, if any, otherwise to a new conversation.
• If the Settings > Notifications > User email notifications option is active, all users with an email are notified via email.
• If the Settings > Notifications > Text message notifications > Active for users option is active, all users with a phone number are notified via text message.
• If the Settings > Notifications > Push notifications option is active, a push notification is sent to all users.
• The message is also sent to messaging apps such as WhatsApp and Messenger if the user is connected to them.
• To send a message to all users of a single messaging app enter one of the following strings: whatsapp, messenger, instagram, telegram, twitter, zalo, wechat, viber, line. Enter tickets to send a message only to the users who created a CHAT.devad.io ticket via the Tickets app.

• Email header and email signature are automatically included in all emails, set them from Settings > Notifications.
• The HTML language is supported.
• The subject supports merge fields.

• To enable direct text messages you must enable the SMS in Settings > Notifications > Text message notifications.

To understand how notifications work and when they are sent read the information below. If you think notifications are not working, most probably you’re just testing them in the wrong way, please read the information below before asking for support.

Both agents and users can receive an email notification when a new message is received.

• When a user sends their first message, if the conversation is assigned to a department, an email is sent only to the agents assigned to that department, if the conversation is assigned to a specific agent, an email is sent only to that agent, otherwise an email is sent to all agents who are not online at the moment. Subsequent emails are sent only to the last agent in the conversation.
• Email notifications are sent only if the last agent in the conversation is offline.
• If you’re using the Artificial Intelligence app, and the human takeover feature is activated, no emails are sent if the chatbot knows the answer.
• To prevent admins from receiving email notifications check Settings > Notifications > Do not send email notifications to admins.

• When an agent sends a message to a user, an email is sent to the user only if the user is offline.
• Only 1 email is sent. Subsequent messages will not trigger a new email alert.

To manage the emails and create the contents go to Settings > Notifications. You can use text and HTML. New lines are automatically converted to <br />. You can use the following merge fields in the email. Merge fields are automatically replaced with the updated information.

• When an agent click the notification the admin area is open and the right conversation is selected. If the admin area is already open the notification will not open a new tab.
• When a user sends their first message, a Push notification is sent to all validated agents; subsequent notifications are sent only to the last agent in the conversation.
• If you’re using the Artificial Intelligence app, and the human takeover feature is activated, no notifications are sent if the chatbot knows the answer.
• If you’re using the WordPress version, Push notifications are not supported in the WordPress admin area, you need to access the CHAT.devad.io admin area directly, more details here.
• If the Routing setting is active, only the agent assigned to the conversation receive the notification, admins see all conversations but don’t receive notifications.
• If queue or routing settings are active, only the agent assigned to the conversation receive the notification. Notifications are not sent for messages sent by the user while waiting in queue. Admins see all conversations but don’t receive notifications.
• If a user conversation is assigned to a department, only the agents assigned to that department receive the notification.
• If a user conversation is not assigned to any department, only agents with no assigned department receive the notification.
• Notifications are sent only if the last agent in the conversation is offline.
• If human takeover is active, no notifications are sent if the chatbot knows the answer.
• If Push notifications are not working, make sure you allowed the notifications, in Chrome you can check this from Privacy and Security > Site settings > Notifications. If they don’t work on a mobile device, try these steps too: install the PWA or delete it and install it again, restart the mobile device.
• If you are using Chrome, to enable Push notifications also when the tab is closed you must enable the Continue running background apps when Google Chrome is closed option from Chrome > Setting > System (chrome://settings/system).
• If Push notifications are not working, make sure that the conversation is not assigned to a specific agent or a wrong agent ID. Click here for more details.
• If Push notifications are not working, and you are using Windows, ensure that the notification feature is not being blocked by Windows. To do this, click on the Start button and search for Notifications. Then, open the Turn app notifications on or off option and verify that your browser is not being blocked.
• If Push notifications are not working, ensure that the CHAT.devad.io admin area is not visible and open. If the admin area is open, please minimize it or open another window or browser tab.
• If Push notifications are not working, your system might be blocking them. If you are using Windows 10+ check this link. If you are on Mac check this link. For all devices also check this link.

• Desktop notifications are not sent if the user is viewing a page with include the chat (the user browser is open and visible, and the active page contains the chat).
• Desktop notifications are not supported on iPhone and iOS devices.
• Desktop notifications work only for secure URLs that use HTTPS (not HTTP). Your CHAT.devad.io admin URL must use HTTPS.
• When Push notifications are active, they replace desktop notifications.
• If desktop notifications aren’t working, try the solutions in the Push notifications section.

Both agents and users can be notified via text message when a new message comes in. Text message notifications are provided by Twilio. Twilio is a paid service, but it is cheap, and you can use the trial version to test text message notifications for free. Text messages sent to your Twilio phone number can also be received in CHAT.devad.io. This allows you to chat with users via SMS in a true two-way messaging experience. More details below.

• Go to https://www.twilio.com and create a new account.
• Verify your phone number.
• Complete the form and choose SMS.
• Once into the dashboard, click Get a Trial Number, then Choose this number.
• Enter the CHAT.devad.io admin area, go to Settings > Notifications > Text message notifications, and paste account SID, auth token, trial number (or a purchased phone number). Find all details in the Twilio dashboard.
• If you’re using the trial version, you can send notifications only to verified numbers. Enter the Twilio dashboard and click the left button # (Phone Numbers), then click Verified Caller IDs and add your phone number.
• To start using the service live and to receive text messages in CHAT.devad.io you need to purchase a phone number. After the purchase go to Phone numbers > Manage > Active numbers, click your number, and enter the URL of CHAT.devad.io, get it from CHAT.devad.io > Settings > Notifications > Text message notifications > Get configuration URL.
• You’re done.

• Ensure that your agents and admins are assigned a phone number so that agent text messages can be sent to the appropriate numbers.
• All phone numbers must have the country code starting with the symbol + (eg. +15558675310).
• You can get the user’s phone number via registration form, follow-up message, or via [email] shortcode. You can manually enter the user phone from the admin area or via API.
• When a user sends their first message, if the conversation is assigned to a department, a test message is sent only to the agents assigned to that department, if the conversation is assigned to a specific agent, a text message is sent only to that agent, otherwise an text message is sent an email is sent to all agents who are not online at the moment. Subsequent text messages are sent only to the last agent in the conversation.
• Text message notifications are sent only if the last agent in the conversation is offline.
• If you’re using the Artificial Intelligence app, and human takeover is active, no text messages are sent if the chatbot knows the answer.
• To use the Sender ID feature enter the sender name in the Sender number field.

• When Settings > Notifications > Sounds are enabled, a sound will play whenever a new message or conversation is received.
• Audio will only play when the user or agent engages with the document by clicking somewhere in the admin area or on the page displaying the chat widget. This is because of a security feature of the browsers.
• If the sound is set to repeat, it will loop as long as the admin area or the chat widget page is not open or minimized. If the the admin area or the chat widget page is open and visible, you will not hear the sound.

Unlock the full potential of your support system with these advanced configuration options. Beyond the basics, CHAT.devad.io offers a suite of powerful tools designed to enhance accessibility, security, and performance. This guide covers how to deploy the Progressive Web App (PWA) for a native-like experience, utilize keyboard shortcuts for rapid management, and configure URL parameters for dynamic automation. Additionally, we will explore the robust security protocols—including IP banning and AES-256 encryption—that protect your data, alongside performance tuning options to ensure lightning-fast load times.

Progressive Web App (PWA)

The CHAT.devad.io admin area functions as a Progressive Web App (PWA). This technology allows you to install the administration panel directly onto your desktop, Mac, iPhone, or mobile device, enabling you to use it just like a fully functional native application. By installing the PWA, you gain faster access to your chats and a more immersive interface without needing to open a browser tab every time.

Note: This feature is fully supported on all versions of CHAT.devad.io and is optimized specifically for Google Chrome and Safari browsers.

Keyboard Shortcuts

To maximize efficiency, admin area keyboard shortcuts are enabled by default for both PC and Mac users. These shortcuts allow agents to navigate the interface, manage conversations, and perform actions without navigating away from the keyboard.

URL Parameters Configuration

URL parameters allow you to trigger specific behaviors automatically when the page loads. This is useful for marketing campaigns, direct user support links, or deep linking into the admin panel.

Front-end Chat Parameters

Append these parameters to any URL on your website where the chat widget is loaded (e.g., https://example.com/?conversation=1234).

Admin Area Parameters

These parameters are designed for the administration panel URL (e.g., https://chat.devad.io/?setting=123 or https://www.yoursite.com/script/admin.php?area=users).

Calendly Integration

You can seamlessly integrate Calendly booking invitations into your chat flows using Rich Messages. Follow these steps to set up a “Schedule a Meeting” button.

1. Create an event type from your Calendly dashboard (e.g., https://calendly.com/event_types/user/me).
2. Click Share and copy the generated URL.
3. To send the invitation in chat, use the button rich message type.
4. Paste your Calendly URL into the link attribute.
5. Crucial Step: Include the success attribute. This defines the confirmation message sent to the user automatically once the booking is completed.

Code Example:

[button link="https://calendly.com/your-link" name="Schedule a meeting" success="Thank you! Your meeting has been scheduled."]

Security Protocols

Security is paramount at CHAT.devad.io. We work with security experts to perform periodic audits and implement the latest technologies to counter threats. Below is a detailed breakdown of the implemented security measures.

Performance Optimization

CHAT.devad.io is engineered for speed, featuring extremely lightweight JavaScript and CSS files that are significantly smaller than competitors. The system is modular, framework-free, and fully optimized. However, you can further fine-tune performance via Settings > Miscellaneous > Performance optimization.

• Minify JS: Enable this to load minified versions of JavaScript and CSS files for the front-end widget, reducing file size and improving loading speed.
• Disable reports: Stops the system from collecting and recording report data, saving valuable server resources.
• Disable articles: Turns off the Knowledge Base/Articles functionality completely, preventing associated resources from loading on both the admin and client sides.
• Archive old messages: Automatically moves messages older than a specified interval to a dedicated backup table. These messages will disappear from active views, drastically improving performance if you handle millions of messages. Note: If a user sends a new message to an archived conversation, the system automatically restores the history. You can also manually restore conversations from the user’s profile.

Customization & Services

You have full freedom to edit the source code of the CHAT.devad.io PHP and WordPress versions to fit your specific needs (see terms of service). While the Cloud version’s source code is not directly editable, it supports extensive customization via the JavaScript API, Web API, and custom CSS. Since the chat widget does not use an iframe, styling it with custom CSS is seamless and effective.

Hire Us

If you require specific customizations but lack the resources to implement them, our team is available for hire. We can tailor CHAT.devad.io to your exact requirements. Our hourly rate is 100 USD. To request a quote based on the complexity of your project, contact us via the support chat in the bottom right corner or email us at [email protected]. We typically reply within 24 hours.

Managing Languages and Translations

effective communication requires speaking your user’s language. In this section, you will learn how to set up CHAT.devad.io to automatically detect user preferences or force specific language settings via URL parameters and WordPress configurations. We also explain how to translate knowledge base articles, customize specific text strings, and even add support for entirely new languages by editing system files.

• You can add new article translations by opening an article. Click the + icon on top right and select the language you want to translate the article into. To delete a translation, hover the language flag icon and click the trash icon.
• You can add new category translations by opening a category. Click the + icon on top right and select the language you want to translate the category into. To delete a translation, hover the language flag icon and click the trash icon.
• You can enable automatic translation of articles and categories by activating both the multilingual via translation feature and Settings > Articles > Language > Automatic translation. You also have to set the default language of your articles from Settings > Articles > Language > Default language. The language used for the automatic translation is the user’s language detected by CHAT.devad.io. You can also force a specific language by adding the URL parameter lang=LANGUAGE-CODE.
• The language menu is shown at the bottom of the article. It shows all the available translations of the article.
• If there is at least one translated article in the user’s language, only the translated articles are displayed in the category page or main page. Otherwise, all articles are displayed in the original language.
• Force the articles page to be shown in a specific language by adding the URL parameter lang=LANGUAGE-CODE. Replace LANGUAGE-CODE with the two-letters language code.

• If you use categories, all the articles must be assigned to a category.
• You can create an internal chat link to an article with the button rich message.
• You can create a link to a specific article with the URL attribute article=ID, replace ID with the article ID. Example: https://chat.devad.io/articles-demo?article=Ucsx6.
• You can create a link to an article category with the URL attribute category=ID, replace ID with the category ID. Example: https://chat.devad.io/articles-demo?category=LnNaZ.
• The articles are always included into the training of your OpenAI chatbot. If you update an article, you’ll need to train the chatbot again, the process isn’t automatic.
• If some block is not saved, e.g. text block, disable all browser extentions and try again.
• To hide the chat widget insert the following code into the articles page: .

CHAT.devad.io is fully multilingual and provides powerful features to detect the user’s language on the fly.

CHAT.devad.io is already translated into 45+ languages. There are many options available to set the language:

• OPTION 1 Go to Settings > Chat and check the Language option. Set it to multilingual to automatically use the chat language of the user’s browser or the language saved in the user profile.
• OPTION 2 Add the URL parameter lang=LANGUAGE-CODE to the script that loads the chat, replacing “LANGUAGE-CODE” with the two-letters language code you would like to display. E.g. or https://chat.devad.io/account/js/init.js?id=123456&lang=es for the cloud version. This feature will force the chat to always use the same language and the Settings > Chat > Language option will be ignored. Go to wikipedia.org/wiki/List_of_ISO_639-1_codes for the complete languages code list (see column 639-1). For Traditional Chinese use zt, for Simplified Chinese use zh, for Brazilian Portuguese use pt.
• OPTION 2 – WORDPRESS ONLY Go to Settings > WordPress and set the option Force language. This feature will force the chat to always use the same language and the Settings > Chat > Language option will be ignored.
• OPTION 3 – WORDPRESS ONLY The WordPress version of CHAT.devad.io uses the default language of the WordPress installation; or the language of the current page or post if the website is multilingual. This feature is compatible with WPML, Polylang, and other multilingual plugins. This feature is automatically disabled if the Settings > Chat > Language option is active.

To translate the admin area follow the steps below:

• Translate the texts in your language from the Settings > Translations.

To set the admin area language you have three options:

• Activate the option Settings > Admin > Automatically translate admin area. This feature automatically translate the admin area to match the agent profile language or the agent browser language.
• Edit the file config.php inside your CHAT.devad.io installation directory and Enter the code define(‘SB_ADMIN_LANG’, ‘LANGUAGE-CODE’); at the end of the file content. Replace LANGUAGE-CODE with the language code of the language you want to use, use only 2 letters, for example, insert only es, not es_ES. This option is not available in the cloud version.

To automatically translate chatbot messages and other texts, use the Artificial Intelligence app and follow the steps outlined here.

You can translate almost any custom content like rich messages, built-in messages, departments, chat header, and more. To add a new translation or edit and existing translation, follow the steps below:

• Go to Settings > Translations, if you want to add a new translation, click New translation.
• Enter the English content you wish to translate in the first field. The original text must be in English. If the original text has breaklines, replace them with the n code.
• Enter the corresponding translation in the second field. To add breaklines, use the n code.
• If you have the artificial intelligence app you can also translate all contents to any language automatically through the multilingual via translation feature.

To add a new language, follow the steps below:

• Via FTP or a File Manager, go to scriptresourceslanguagesfront.
• Duplicate (copy and paste it in the same directory) the scriptresourceslanguagesfrontsource.json file.
• Rename the file with the language code you would like to add. Go to wikipedia.org/wiki/List_of_ISO_639-1_codes for the complete languages code list (see column 639-1).
• Go to Settings > Translations and the new language should appear automatically.

To add a new language for the admin area, follow the exact same steps, but use folder admin instead. New languages will not be lost or deleted on plugin updates.

• If a translation string is missing, add it by clicking the button Add new translation.
• If a translation string is not working, make sure to remove all white spaces and break lines at the start and the end of the string.
• The translations edits are not saved in the database but directly in the translation files. When a translation is edited, and saved, a backup is created into the uploads folder. The backup is restored automatically on plugin update and plugin activation.
• Some special chars like & are replaced by the HTML equivalent code (see https://www.w3schools.com/html/html_entities.asp). Ex. & is replaced by &.
• You can add missing translation strings also by code. Edit the language files located in scriptresourceslanguages. After editing a file, the new strings will be visible under Settings > Translations. Remember to click Save changes in order to preserve your translations and avoid losing them when CHAT.devad.io is updated.

The feature Artificial Intelligence > Google > Multilingual checks if there is a Dialogflow agent in the user’s language and activate it.

• For this feature to work the user language must be know. The user language is based on the language user detail of the user if set, otherwise on the user browser language. The language can also be detected with the language detection feature.

The automatic translation feature automatically translates user messages into agent language and agent messages into user language. To enable it check the option Settings > Artificial Intelligence > Automatic translation. If you are using the cloud version and Artificial Intelligence > Google > Sync mode is set to Automatic, the multilingual features will work automatically. Otherwise you have to complete the synchronization and the setup below. The multilingual via translation and language detection features also require these steps.

• Log in to https://console.cloud.google.com with your Google account and select the project of your Dialogflow Agent.
• On the top search bar type cloud translation, select the Cloud Translation API service and enable it. Please note that this is a paid service with a free tier, additional charges may occur.
• Enable the billing by clicking Left menu > Billing and by enabling a billing account with a valid payment method.

• The user messages in the admin area are translated automatically in real-time to match the agent language.
• The agent messages are translated automatically in real-time to match the user language.
• Agents can view the original message by opening the message menu and by clicking View original message.
• The agent language is based on the language user detail of the agent if set, otherwise on the browser language, or admin area language.
• The user language is based on the language user detail, if set, otherwise on chat language, if set, otherwise on the browser language. The language can also be detected with the language detection feature.
• The notifications are also translated.
• To avoid translating a string, enclose it with the characters ` or “`.

The feature at Settings > Artificial Intelligence > Multilingual via translation automatically translates user messages into the default language of Dialogflow or OpenAI, and translates Dialogflow or OpenAI messages into the language spoken by the user. Additionally, this feature translates all text displayed within the chat, such as the chatbot’s rich messages, articles, registration forms, and pop-up notifications. To enhance performance and minimize translation costs, the translations are automatically integrated into the translation files. Combine this feature with the language detection feature for optimal results.

• If English is one of the languages, English must be the default language, the original texts must be in English.
• If you are using OpenAI with training data, set the default training data language under Settings > Artificial Intelligence > OpenAI > Training Sources Language. Leave it as default if the training data default language is in English.

Detect the language of the user’ messages and change the user language and Dialogflow agent language accordingly, if available, otherwise, show a fallback message. You can use the following merge fields in the message: {language_name}.

• The user message must be at least 2 words long.
• Language detection is executed only for the first 2 user messages of a conversation.
• As long as the OpenAI chatbot is operational and programmed to respond to generic inquiries, the fallback message will never be dispatched, since OpenAI will consistently provide answers to any use message.

• The supported AI features include language detetction, spelling correction, multilingual via translation, Google search.

Knowledge Base & Ticket Management

Expand your customer support capabilities beyond real-time chat. This guide covers two essential modules: Articles and Tickets. Learn how to build a searchable Knowledge Base that reduces support volume and automatically trains your AI chatbot. Additionally, discover how to implement a structured Ticketing system for handling complex inquiries. Below, you will find installation steps, display methods (including WordPress shortcodes and script modifications), and advanced configuration options for both tools.

Articles (Help Center)
Empower your users to find instant answers and significantly reduce your support team’s workload. The Articles module allows you to create a fully integrated Knowledge Base that can be displayed directly in the chat dashboard, sent via rich messages, or hosted on a dedicated page. These articles also serve as a dynamic training source for your AI chatbot, ensuring your automated responses stay up-to-date.
Knowledge base articles provide instant answers to customers to help reduce customer support volume. You can access the articles from the left CHAT.devad.io menu.

• The articles can be shown in the chat dashboard by enabling them from Settings > Articles > Display in dashboard.
• Alternatively, articles can be shared in any chat conversation via the rich message shortcode, [articles].
• Follow these steps to display the articles on a page of your domain and website. You can display them in three ways:

The page shows the article categories, you must add parent categories and assign articles to them. The articles will be shown in the same location of the code above. You can hide the chat widget by adding the JS code var SB_DISABLED = true; to the page.

The article’s one-page navigation appears automatically on all articles. It is generated from the article’s h2 and h3 heading blocks.

To show Articles in your websites, use this code in your page. dont forget to add your API token which can be found in https://chat.devad.io/account/?tab=installation

Another option is to install this javascript into a new page.
please note that to use the JS method you need to include the installation script code like in your page where you want to display or use the chat. This script initializes the chat system on your site.

If you see 404 error, The 404 error on other pages when displaying articles means that the article categories or articles are not properly loaded or linked on those pages.
To fix this: Ensure the URL parameter for category or article_id is set correctly on those pages to load the right content.
Configure your website routes or permalinks so that requests for articles don’t lead to 404 errors.
Make sure parent categories and articles are assigned properly in the Support Board admin area.
Optionally, use the REST API or PHP API method to load articles dynamically with proper parameter handling.
In brief, 404 means the pages are missing or not mapped properly to article content. You need to configure URLs and categories so that articles display correctly on all pages.

This training process enables you to train the chatbot using the articles.

• To train the chatbot add you articles and than click the Train chatbot button. The articles are used as training sources automatically.
• For more details click here.
• Articles All article languages are used automatically.
• CHAT.devad.io articles are synchronized automatically with the Dialogflow knowledge base.

When this option is active, the response will automatically include the links to the sources and training data used for generating the answer. To include articles as sources you have first to set the articles page in Settings > Articles > Articles page URL.

The system is extremely lightweight, built without frameworks or unnecessary code. It’s modular, minimal, and fully optimized for maximum performance.

Disable articles: Disable the articles area and article functionality. This reduces resource usage by preventing the system from loading articles on both the admin and client sides.

The Tickets app offers an alternative way for users to submit inquiries, providing a structured interface distinct from the standard chat widget. While it shares the same powerful backend as the chat system, the frontend is designed for creating and tracking longer-form requests. Whether you are using WordPress or a custom website, the guide below explains how to activate the app and display the ticket area using simple shortcodes or URL parameters.
The settings below are related to the Tickets app. The Tickets app allows users to create conversations and send messages via a UI different from the chat.

• From Settings > Apps, click Tickets and click Active.

WordPress

To display the tickets use the shortcode

[sb-tickets]

Insert it in any page, post, or post type item.

Any Website

To display the tickets area include the chat embed code into your page and add the attribute &mode=tickets to the script URL, e.g.

. You can show the tickets area also by inserting the code into any page showing the chat.

• If the tickets area is not visible, make sure to uncheck the option Tickets > Manual initialization. Additionally, you can explore other potential reasons for this issue here.
• You can also use the tickets area to display an inline or full-width chat panel.
• Tickets are the same of chat conversations on the admin-side, the only difference from chat conversations is the front-end UI.
• Most of the settings of the chat are compatible with the Tickets App but not all of them. The dashboard settings, the pop-up message, and more are not compatible.
• Dedicated APIs for the Tickets App are available in the API section.
• To remove the mandatory ‘New ticket’ form for new users, activate the welcome message of Settings > Messages & Forms > Welcome message. The welcome message delay is ignored in the tickets area, the message is sent immediately..
• To manually disable the mandatory registration only on a single page use the JavaScript code var SB_REGISTRATION_REQUIRED = true. Set it to true to force the registration instead.
• The tickets area is compatible with Google reCaptcha v3.

Team Workflow & Conversation Routing Settings

Scale your support operations with powerful distribution and organization tools.

• Departments: Segment your team (e.g., Sales, Support) and route conversations accordingly.
• Queue & Routing: Automatically distribute incoming chats to available agents or place users in a waiting line when demand is high.
• Email Piping: Seamlessly integrate your email inbox, allowing agents and users to reply to chat messages directly from their email clients.
• Office Hours: Define your team’s availability to trigger offline messages or hide the chat widget outside of business hours.

Departments give you the power to distribute conversations and assign various agents to specific departments. For example, you can create a department entitled “Sales” and assign specific conversations to that department. To start using departments, follow the steps below:

• Go to Settings > Miscellaneous and add, delete and manage the departments. After saving, reload the page.
• Go to Users > Agents and edit an agent, you will see a new field where you can set the department of the agent.
• Reload the page and you’re done! In the Conversations area, you will now see an option to set the department.

• Display in dashboard Displays the departments’ list in the chat dashboard and force users to choose a department before starting a conversation.
• Display images Displays the department image instead of the department color.
• Display in conversation list Displays the department color in the conversation list of the admin area.
• One conversation per department Restrict users from opening multiple conversations within the same department, allowing only one conversation to be active per department.
• Label Replace the label Departments (plural) with another text. The name is displayed in the admin and tickets area.
• Label single Replace the label Department (singular) with another text. The name is displayed in the admin and tickets area.
• Dashboard title Set the title of the chat dashboard list. Default: Departments.

• Agents and admins with no assigned department always see the conversations of all departments.
• Agents and admins with an assigned department can only access conversations, users, and agents within that department.
• When a conversation is assigned to a new department, an email notification is sent to all of the agents assigned to the new department.
• The chatbot can assign a department to the active conversation through the Q&A set data feature, the flows actions feature, or Dialogflow actions.

You can assign a department to a conversation in several ways:

• Via the Q&A set data feature.
• Via the flows actions feature.
• Via Settings > Miscellaneous > Departments settings > Display in dashboard. In this case, the user will be required to select a department before starting a new conversation.
• Via Settings > Automations > More.
• Via JavaScript, with the variable var SB_DEFAULT_DEPARTMENT = ID;. Enter the code into the pages where the chat is displayed and replace ID with the department ID. For more details check the API here.
• Via API.

If the Settngs > Slack > Department linking option is active, when a conversation in the CHAT.devad.io is assigned to a department, a new message is sent to the linked Slack channel, informing Slack users that a new conversation has started and inviting them to join the dedicated user Slack channel. However, the full conversation can only be accessed on the dedicated Slack channel of the specific user.

• Get the department IDs from Settings > Miscellaneous > departments.
• Get the channel IDs by clicking the button Get channel IDs.

When the queue is activated via Settings > Miscellaneous > Queue, or routing is activated via Settings > Miscellaneous > Routing, CHAT.devad.io automatically assigns the users conversations to all available agents proportionately.

• Only online agents are counted as “available” agents and will receive new conversations. Conversations are assigned proportionally between all online agents. If no agents are online, the conversation will remain unassigned and will be automatically assigned to the first agent who comes online.
• Admins are not included; admins always see all the conversations.
• Agents must archive a conversation to mark it as completed; this will automatically give them access to the next conversation in the queue. A conversation is active if it’s not deleted, or archived.
• Agents can switch their status between online and offline by hovering over their profile image and then clicking the label of the profile pop-up at the bottom-left of the admin area.
• Agents can only search and filter their conversations.
• Agents can only view their conversations; however, they can see all of the conversations of a single user.
• To enable agents to view all unassigned conversations, activate Settings > Miscellaneous > Hide conversations of other agents and View unassigned conversations.
• Queue and routing are compatible with the departments.
• If human takeover is active, the queue or routing is activated only on human takeover.
• When routing or queue is active, the agents menu will be automatically enabled.

When the queue is activated users enter into a queue automatically when an agent’s chat limit is reached. When a user enters the queue, a message with the current position in the queue and the estimated waiting time is displayed. CHAT.devad.io automatically assigns the conversations to all available agents proportionately. When an agent marks a conversation as completed (by archiving it), the queue is updated and a new conversation is received.

• If a user is in the queue and leaves (e.g. by closing the browser) for more than 1 minute, the conversation is saved; however, once the user comes back, the queue is reset and the user will lose their previous position. If the user leaves, the conversation remains unassigned and therefore invisible to agents, but only visible to admins.
• You can use the following merge fields in the queue message: {position}, {minutes}. They will be replaced by the real values in real-time.
• The waiting time is displayed in minutes and is calculated as follows: queue position X response time = waiting time. For example, if a user is 5th in the queue, and the response time has been set to 4 minutes (via Settings > Miscellaneous > Queue), then the total wait time displayed to the user will be 20 minutes.
• When the sound option is active, a sound is played when it’s the user’s turn.
• For conversations started from messaging apps like WhatsApp, it is not possible to respect the limit of conversations per agent, all conversations will be immediately and proportionally assigned to an online agent. If no agents are online, the conversation will remain unassigned and will be automatically assigned to the first agent who comes online.
• Use the offline message to prevent the chat from showing the queue update message to the user.

To test the queue, follow the steps below:

• To simulate multiple users and agents, open the chat in multiple different browsers (e.g. Opera, Firefox, Brave, Chrome, etc.). Each browser can simulate two users/agents: one in normal mode and one in “private” or “incognito” mode.
• To reset the chat and start a new user session, open the browser console, enter SBF.reset(), and press ENTER.

When the routing is activated CHAT.devad.io automatically assigns the users conversations to all available agents proportionately.

• If the Routing > Disable online status check option is active, the conversations are distributed proportionally among all agents, regardless of whether they are online or offline.
• When an agent comes back online after being offline, all unassigned conversations are automatically assigned to them.
• When routing is active agents can manually route conversations to other agents from the right panel of the conversations area.
• If the conversation is archived and the user reopens it in the future by sending a new message, if the assigned agent in the conversation is offline, the conversation is assigned to another agent.

When the routing is activated via Settings > Miscellaneous > Hide conversation of other agents agents see only their own conversations and can select the unassigned ones.

• Agents menu: enable the agents menu.
• Routing if offline: if the conversation is archived and the user reopens it in the future by sending a new message, if the assigned agent in the conversation is offline, the conversation is assigned to another online if there is at least one, otherwise to no agent.
• View unassigned conversations: allow agents to view the unassigned conversations, when an agent replies the conversation is automatically assigned to him and the conversation is removed in real-time from the admin area of the other agents. Check this option to enable the manual routing.

The Agents menu lets you assign conversations to specific agents. It appears on the right side of the conversations area and is automatically enabled when queueing or routing is active. Select multiple conversations (see keyboard shortcuts) to assign the selected conversations to a specific agent.

You can assign an agent to a conversation in several ways:

• Via the Q&A set data feature.
• Via the flows actions feature.
• Via the queue or routing features.
• By enabling the Settings > Chat > Agents menu option. In this case, the user will be required to select an agent before starting a new conversation.
• Via Settings > Automations > More.
• Via JavaScript, with the variable var SB_DEFAULT_AGENT = ID;. Enter the code into the pages where the chat is displayed and replace ID with the agent ID. For more details check the API here.
• Via API.

Email piping lets you sync multiple email addresses to receive messages directly in CHAT.devad.io. It also allows you, your agents, and users to reply to chat messages via email.

• Go to Settings > Notifications > Email piping and enter your POP3/IMAP email server information.
• Go to Settings > Notifications > SMTP and enter your SMTP email server information. The email address must be the one to which the email piping server connects to. CHAT.devad.io will send all emails from this email address and you, your agents, and your users will reply to this email address. For more details check the email notifications section.

• The email address of Settings > Notifications > SMTP > Sender email should match the one used by the email piping server. If the email address does not match, or if multiple email addresses are configured for email piping, and the Username setting is defined as an email address, CHAT.devad.io will automatically include a reply-to field in the email notification. This ensures that when the user replies, their response is directed to the correct email piping address, keeping the conversation linked properly.
• The Notifications > User email notifications and Notifications > Agent email notifications settings are enabled automatically when email piping is active. When agents reply in CHAT.devad.io, emails are always sent to the user.
• If you’re using the Artificial Intelligence app, and the human takeover feature is activated, no emails are sent if the chatbot knows the answer.
• If the Convert all emails option is active:

You can set the office hours timetable from Settings > Miscellaneous > Office hours. Office hours are used for:

• Sending the offline message.
• Disabling and hiding the chat during out-of-office hours.
• Disabling the chatbot during regular office hours and enabling it during out-of-office hours.

• If a day has only one start and end time, enter them in the first two fields. For example, use 10:00 AM to 5:00 PM and (empty) to (empty), not 10:00 AM to (empty) and (empty) to 5:00 PM.
• Do not leave empty values. Set them to closed instead.
• You have to set values to closed if you want to set a whole day as not office hours.
• The office hours are in UTC format. Set your UTC from Settings > Miscellaneous > Timezone.
• The date and time format of the timetable matchs automatically the one used in the country of the browser language of the user.

Managing Languages and Translations

effective communication requires speaking your user’s language. In this section, you will learn how to set up CHAT.devad.io to automatically detect user preferences or force specific language settings via URL parameters and WordPress configurations. We also explain how to translate knowledge base articles, customize specific text strings, and even add support for entirely new languages by editing system files.

• You can add new article translations by opening an article. Click the + icon on top right and select the language you want to translate the article into. To delete a translation, hover the language flag icon and click the trash icon.
• You can add new category translations by opening a category. Click the + icon on top right and select the language you want to translate the category into. To delete a translation, hover the language flag icon and click the trash icon.
• You can enable automatic translation of articles and categories by activating both the multilingual via translation feature and Settings > Articles > Language > Automatic translation. You also have to set the default language of your articles from Settings > Articles > Language > Default language. The language used for the automatic translation is the user’s language detected by CHAT.devad.io. You can also force a specific language by adding the URL parameter lang=LANGUAGE-CODE.
• The language menu is shown at the bottom of the article. It shows all the available translations of the article.
• If there is at least one translated article in the user’s language, only the translated articles are displayed in the category page or main page. Otherwise, all articles are displayed in the original language.
• Force the articles page to be shown in a specific language by adding the URL parameter lang=LANGUAGE-CODE. Replace LANGUAGE-CODE with the two-letters language code.

• If you use categories, all the articles must be assigned to a category.
• You can create an internal chat link to an article with the button rich message.
• You can create a link to a specific article with the URL attribute article=ID, replace ID with the article ID. Example: https://chat.devad.io/articles-demo?article=Ucsx6.
• You can create a link to an article category with the URL attribute category=ID, replace ID with the category ID. Example: https://chat.devad.io/articles-demo?category=LnNaZ.
• The articles are always included into the training of your OpenAI chatbot. If you update an article, you’ll need to train the chatbot again, the process isn’t automatic.
• If some block is not saved, e.g. text block, disable all browser extentions and try again.
• To hide the chat widget insert the following code into the articles page:

  <script>var SB_DISABLED = true;</script>

  .

CHAT.devad.io is fully multilingual and provides powerful features to detect the user’s language on the fly.

CHAT.devad.io is already translated into 45+ languages. There are many options available to set the language:

• OPTION 1 Go to Settings > Chat and check the Language option. Set it to multilingual to automatically use the chat language of the user’s browser or the language saved in the user profile.
• OPTION 2 Add the URL parameter lang=LANGUAGE-CODE to the script that loads the chat, replacing “LANGUAGE-CODE” with the two-letters language code you would like to display. E.g. or https://chat.devad.io/account/js/init.js?id=YOUR-CHAT-ID&lang=es for the cloud version. This feature will force the chat to always use the same language and the Settings > Chat > Language option will be ignored. Go to wikipedia.org/wiki/List_of_ISO_639-1_codes for the complete languages code list (see column 639-1). For Traditional Chinese use zt, for Simplified Chinese use zh, for Brazilian Portuguese use pt.
• OPTION 2 – WORDPRESS ONLY Go to Settings > WordPress and set the option Force language. This feature will force the chat to always use the same language and the Settings > Chat > Language option will be ignored.
• OPTION 3 – WORDPRESS ONLY The WordPress version of CHAT.devad.io uses the default language of the WordPress installation; or the language of the current page or post if the website is multilingual. This feature is compatible with WPML, Polylang, and other multilingual plugins. This feature is automatically disabled if the Settings > Chat > Language option is active.

To translate the admin area follow the steps below:

• Translate the texts in your language from the Settings > Translations.

To set the admin area language you have three options:

• Activate the option Settings > Admin > Automatically translate admin area. This feature automatically translate the admin area to match the agent profile language or the agent browser language.
• Edit the file config.php inside your CHAT.devad.io installation directory and Enter the code define(‘SB_ADMIN_LANG’, ‘LANGUAGE-CODE’); at the end of the file content. Replace LANGUAGE-CODE with the language code of the language you want to use, use only 2 letters, for example, insert only es, not es_ES. This option is not available in the cloud version.

To automatically translate chatbot messages and other texts, use the Artificial Intelligence app and follow the steps outlined here.

You can translate almost any custom content like rich messages, built-in messages, departments, chat header, and more. To add a new translation or edit and existing translation, follow the steps below:

• Go to Settings > Translations, if you want to add a new translation, click New translation.
• Enter the English content you wish to translate in the first field. The original text must be in English. If the original text has breaklines, replace them with the n code.
• Enter the corresponding translation in the second field. To add breaklines, use the n code.
• If you have the artificial intelligence app you can also translate all contents to any language automatically through the multilingual via translation feature.

To add a new language, follow the steps below:

• Via FTP or a File Manager, go to scriptresourceslanguagesfront.
• Duplicate (copy and paste it in the same directory) the scriptresourceslanguagesfrontsource.json file.
• Rename the file with the language code you would like to add. Go to wikipedia.org/wiki/List_of_ISO_639-1_codes for the complete languages code list (see column 639-1).
• Go to Settings > Translations and the new language should appear automatically.

To add a new language for the admin area, follow the exact same steps, but use folder admin instead. New languages will not be lost or deleted on plugin updates.

• If a translation string is missing, add it by clicking the button Add new translation.
• If a translation string is not working, make sure to remove all white spaces and break lines at the start and the end of the string.
• The translations edits are not saved in the database but directly in the translation files. When a translation is edited, and saved, a backup is created into the uploads folder. The backup is restored automatically on plugin update and plugin activation.
• Some special chars like & are replaced by the HTML equivalent code (see https://www.w3schools.com/html/html_entities.asp). Ex. & is replaced by &amp;.
• You can add missing translation strings also by code. Edit the language files located in scriptresourceslanguages. After editing a file, the new strings will be visible under Settings > Translations. Remember to click Save changes in order to preserve your translations and avoid losing them when CHAT.devad.io is updated.

The feature Artificial Intelligence > Google > Multilingual checks if there is a Dialogflow agent in the user’s language and activate it.

• For this feature to work the user language must be know. The user language is based on the language user detail of the user if set, otherwise on the user browser language. The language can also be detected with the language detection feature.

The automatic translation feature automatically translates user messages into agent language and agent messages into user language. To enable it check the option Settings > Artificial Intelligence > Automatic translation. If you are using the cloud version and Artificial Intelligence > Google > Sync mode is set to Automatic, the multilingual features will work automatically. Otherwise you have to complete the synchronization and the setup below. The multilingual via translation and language detection features also require these steps.

• Log in to https://console.cloud.google.com with your Google account and select the project of your Dialogflow Agent.
• On the top search bar type cloud translation, select the Cloud Translation API service and enable it. Please note that this is a paid service with a free tier, additional charges may occur.
• Enable the billing by clicking Left menu > Billing and by enabling a billing account with a valid payment method.

• The user messages in the admin area are translated automatically in real-time to match the agent language.
• The agent messages are translated automatically in real-time to match the user language.
• Agents can view the original message by opening the message menu and by clicking View original message.
• The agent language is based on the language user detail of the agent if set, otherwise on the browser language, or admin area language.
• The user language is based on the language user detail, if set, otherwise on chat language, if set, otherwise on the browser language. The language can also be detected with the language detection feature.
• The notifications are also translated.
• To avoid translating a string, enclose it with the characters ` or “`.

The feature at Settings > Artificial Intelligence > Multilingual via translation automatically translates user messages into the default language of Dialogflow or OpenAI, and translates Dialogflow or OpenAI messages into the language spoken by the user. Additionally, this feature translates all text displayed within the chat, such as the chatbot’s rich messages, articles, registration forms, and pop-up notifications. To enhance performance and minimize translation costs, the translations are automatically integrated into the translation files. Combine this feature with the language detection feature for optimal results.

• If English is one of the languages, English must be the default language, the original texts must be in English.
• If you are using OpenAI with training data, set the default training data language under Settings > Artificial Intelligence > OpenAI > Training Sources Language. Leave it as default if the training data default language is in English.

Detect the language of the user’ messages and change the user language and Dialogflow agent language accordingly, if available, otherwise, show a fallback message. You can use the following merge fields in the message: {language_name}.

• The user message must be at least 2 words long.
• Language detection is executed only for the first 2 user messages of a conversation.
• As long as the OpenAI chatbot is operational and programmed to respond to generic inquiries, the fallback message will never be dispatched, since OpenAI will consistently provide answers to any use message.

• The supported AI features include language detetction, spelling correction, multilingual via translation, Google search.

• CHAT.devad.io tries to process emails via cron jobs every 60 seconds, details here.
• If you’re using the cloud version the cron job is already activated by default and it will run at least once every 60 minutes.
• You can manually trigger execution and speed up cron jobs via API with the PHP function sb_email_piping(), or the WEB API function email-piping.
• You can create a cron job that runs the URL https://chat.devad.io/script/include/api.php?piping=true&cloud=API-TOKEN and replace API-TOKEN with your API token.
• If you manually run the cron job, activate the Disable cron job option to stop CHAT.devad.io from manually triggering it and to improve performance.

just enable the Settings > Artificial Intelligence > OpenAI > Training via cron job option and the cron job will be activated. You can disregard the instructions below.

To automatically train the chatbot with your website content at regular intervals, create a cron job that runs the URL https://chat.devad.io/include/api.php?open-ai-training=true, or use the command */59 * * * * wget https://chat.devad.io/include/api.php?open-ai-training=true to run it via a command. Replace https://chat.devad.io with your Installation URL, get it from Settings > Miscellaneous > Installation URL. use this URL: https://chat.devad.io/script/include/api.php?open-ai-training=true&cloud=API-TOKEN and replace API-TOKEN with your API token.

• the cron job can be executed at most once every 7 days.
• We strongly recommand providing an XML sitemap instead of the website URL for performance reasons.
• Automatic training is limited to websites; files, Q&A, and articles are excluded. Re-training will delete the previous website training data.

• Cron jobs are executed by the first user that visit the website at any given hour of the day.
• Cron jobs are executed every 60 minutes (60 seconds for email piping), but it can take longer, or it can take less time as well, in relation to the traffic of your website.
• Because cron jobs are initiated by users, if you have less than 1 visitor per hour (per minute for email piping), it could take longer. As long as there is at least one active user on the site, execution every 60 minutes (60 seconds for email piping) is guaranteed.
• You can speed up the cron jobs execution by manually run them via WEB API, or PHP API.

Automations allow running multilingual automatic tasks when conditions set by you are met.

• To delete a condition, set it to empty. To disable an automation, delete all conditions.
• Automations are sent only 1 time to users.
• If you used an automation in the past, and users already received it, you need to delete the automation and create a new one to show it to the users.
• Repeat only works if used in conjunction with date time.
• When date time is used in conjunction with the criteria is exactly, the value must not contain hours and minutes (hh:mm). Ex. 25/10/2021 (25/10/2021 10:30 will not work).
• The Settings > Users > Register all visitors option must be active if there are message automations that are executed on page load.
• City, countries, languages work automatically only if both the settings Settings > Users > Register all visitors and Settings > Users > Full visitor details are enabled.
• Cities work only if the user detail location is set and equal to city, country, or if the user detail city is set.
• Countries work only if the user details country_code, or country is set, or if the user detail location is set and equal to city, country. The country name must be in english.
• languages work only if the user details browser_language, or language is set.
• A visitor is a Returning visitor only if it visits the website again after 24h or more.
• The pop-ups appear only if the chat is closed, and they overwrite the default pop-up. You can check the message fallback option to send a message instead of showing the pop-up if the chat is open.
• You may need to enable Settings > Users > Register all visitors if you want to send an automated message to new users.
• Chat messages and popup fallback messages are sent only if the last user or agent message of the conversation is older than 10 minutes. This feature prevents unwanted automated messages to be sent during an agent-user conversation.
• The Custom variable condition check for the JavaScript variables with the given names and values. For example, the condition example=ABC is met if into the chat’s page there is this JavaScript code: var example = “ABC”;. Add multiple variables separated by commas.
• Automations are not compatible with the messaging apps like WhatsApp, Messenger, Instagram, Telegram, Twitter, Zalo, WeChat, Viber, Line.

This section contains help for This section contains help for Mobile App and other features not listed above.

The CHAT.devad.io admin area is a PWA, which means that you can install it on desktop, Mac, iPhone, or mobile devices and use it like a fully-functional app. Note: This feature is optimized for Google Chrome and Safari. The PWA is supported on all versions of CHAT.devad.io.

Enter in your admin area (e.g. https://chat.devad.io), and click the + icon on the top right of the URL bar of your Chrome browser. If you are using the WordPress version see the information below.

If you are using the cloud version of CHAT.devad.io on Android you can use the apps available on Google Play. We recommend using the PWA instead of the Android app to have the latest features and updates.

Google Play

• Enter in your admin area with Google Chrome (https://chat.devad.io/)
• Open your browser’s settings.
• Scroll down and tap Add to Home screen.
• Confirm by tapping Add.

• Enter in your admin area with Safari ( https://chat.devad.io/)
• Press the Share button and select Add to Home Screen from the popup.
• Tap Add in the top right corner to finish installing the PWA.

Admin area keyboard shortcuts are enabled on both PC and MAC and work as follows:

URL parameters allow the chat to perform specific actions on page load. To use them, append the URL parameters below to any URL on your website that displays the chat. Ex. https://example.com/?conversation=1234

URL parameters allow the administration area to perform specific actions on page load. To use them, append the URL parameters below to your admin URL. Ex. https://chat.devad.io/?conversation=1234.

?login_email=email&login_password=password

• You can enable the log file from Settings > Miscellaneous > Logs. This feature is not available in the cloud version.
• The log file is saved in the CHAT.devad.io installation directory.
• The logs record the following actions of agents and administrators: message sent, message deleted, conversation archived, conversation deleted, conversation restored, conversation assigned to an agent, conversation assigned to a department, user updated, user deleted.

Security is critical here at CHAT.devad.io. We work with security experts who perform periodic security audits. We continually implement the latest security technologies and stay up-to-date on the latest security threats. Find below some of the security measures that have been implemented in CHAT.devad.io.

CHAT.devad.io permits a maximum of 10 unsuccessful login attempts within an hour. In case the limit is exceeded by a user, admin, or agent, they will be unable to access their account or the admin area for a period of 1 hour. This blocking mechanism is based on the user’s IP address and serves to deter brute force attacks aimed at uncovering login credentials. If you encounter the “Too many login attempts. Please retry again in a few hours.” error, you have two options: either wait for a few hours or make changes to the CHAT.devad.io database by deleting the ip-ban row from the sb_settings table.

To prevent XSS injection protection attacks, all sensitive user inputs undergo sanitization.

To prevent CSRF attacks, all requests are validated by checking the login cookie and the client-side login string.

Whenever the password or the details for an admin or agent is changed, all active sessions are automatically logged out when sensitive operations are executed or after 1 hour.

We use 256-bit AES encryption to encrypt sensitive data such as active session login data.

CHAT.devad.io ensures that all uploads are renamed with a random alphanumeric string prepended to the original file name to prevent discovery of the URL and unauthorized download of the uploaded file. Kindly note that, for this feature to function properly, your server must prohibit directory listing.

CHAT.devad.io is one of the fastest support systems on the market. Its JavaScript and CSS file sizes are significantly smaller than those of most competitors, ensuring faster load times. Server-side performance is equally impressive. The system is extremely lightweight, built without frameworks or unnecessary code. It’s modular, minimal, and fully optimized for maximum performance. Nevertheless, you can further improve performance from Settings > Miscellaneous > Performance optimization. Below is a description of each available optimization setting.

• Minify JS: Enable loading of minified JavaScript and CSS files for the front-end chat widget to reduce file size and improve loading speed.
• Disable reports: Disable the reports area and stop recording report data. This prevents the system from consuming resources to collect and store report-related information.
• Disable articles: Disable the articles area and article functionality. This reduces resource usage by preventing the system from loading articles on both the admin and client sides.
• Archive old messages: Move messages older than the specified interval to a dedicated database backup table. Archived messages and their associated conversations will no longer appear in the admin or user conversation areas. However, if a user sends a new message in the future, the system will automatically restore the conversation and its message history. You can also manually access and restore archived conversations at any time by opening the user’s profile and selecting the archived conversation. Activate this feature if you handle a large volume of messages (in the millions). It will drastically improve performance.

You can fully edit the source code of CHAT.devad.io Web and WordPress versions. See the terms of service for more details. The cloud version source code is not editable, but you can customize it by using the JavaScript API and the Web API, or with JavaScript and CSS. The chat widget does not use an iframe, so you can easily customize it with JavaScript and CSS.

If you want us to customize CHAT.devad.io for you, please contact us and send us your requirements. We will provide you with a quote based on the complexity of the work. Our hourly rate is 25 USD. Contact us throught the chat here on the right bottom corner of the page or email us at [email protected]. We usually reply within 24 hours.

Unlock the full potential of your support system with these advanced configuration options. Beyond the basics, CHAT.devad.io offers a suite of powerful tools designed to enhance accessibility, security, and performance. This guide covers how to deploy the Progressive Web App (PWA) for a native-like experience, utilize keyboard shortcuts for rapid management, and configure URL parameters for dynamic automation. Additionally, we will explore the robust security protocols—including IP banning and AES-256 encryption—that protect your data, alongside performance tuning options to ensure lightning-fast load times.

Progressive Web App (PWA)

The CHAT.devad.io admin area functions as a Progressive Web App (PWA). This technology allows you to install the administration panel directly onto your desktop, Mac, iPhone, or mobile device, enabling you to use it just like a fully functional native application. By installing the PWA, you gain faster access to your chats and a more immersive interface without needing to open a browser tab every time.

Note: This feature is fully supported on all versions of CHAT.devad.io and is optimized specifically for Google Chrome and Safari browsers.

Keyboard Shortcuts

To maximize efficiency, admin area keyboard shortcuts are enabled by default for both PC and Mac users. These shortcuts allow agents to navigate the interface, manage conversations, and perform actions without navigating away from the keyboard.

URL Parameters Configuration

URL parameters allow you to trigger specific behaviors automatically when the page loads. This is useful for marketing campaigns, direct user support links, or deep linking into the admin panel.

Front-end Chat Parameters

Append these parameters to any URL on your website where the chat widget is loaded (e.g., https://example.com/?conversation=1234).

Admin Area Parameters

These parameters are designed for the administration panel URL (e.g., https://chat.devad.io/?setting=123 or https://www.yoursite.com/script/admin.php?area=users).

Calendly Integration

You can seamlessly integrate Calendly booking invitations into your chat flows using Rich Messages. Follow these steps to set up a “Schedule a Meeting” button.

1. Create an event type from your Calendly dashboard (e.g., https://calendly.com/event_types/user/me).
2. Click Share and copy the generated URL.
3. To send the invitation in chat, use the button rich message type.
4. Paste your Calendly URL into the link attribute.
5. Crucial Step: Include the success attribute. This defines the confirmation message sent to the user automatically once the booking is completed.

Code Example:

[button link="https://calendly.com/your-link" name="Schedule a meeting" success="Thank you! Your meeting has been scheduled."]

Security Protocols

Security is paramount at CHAT.devad.io. We work with security experts to perform periodic audits and implement the latest technologies to counter threats. Below is a detailed breakdown of the implemented security measures.

Performance Optimization

CHAT.devad.io is engineered for speed, featuring extremely lightweight JavaScript and CSS files that are significantly smaller than competitors. The system is modular, framework-free, and fully optimized. However, you can further fine-tune performance via Settings > Miscellaneous > Performance optimization.

• Minify JS: Enable this to load minified versions of JavaScript and CSS files for the front-end widget, reducing file size and improving loading speed.
• Disable reports: Stops the system from collecting and recording report data, saving valuable server resources.
• Disable articles: Turns off the Knowledge Base/Articles functionality completely, preventing associated resources from loading on both the admin and client sides.
• Archive old messages: Automatically moves messages older than a specified interval to a dedicated backup table. These messages will disappear from active views, drastically improving performance if you handle millions of messages. Note: If a user sends a new message to an archived conversation, the system automatically restores the history. You can also manually restore conversations from the user’s profile.

Customization & Services

You have full freedom to edit the source code of the CHAT.devad.io PHP and WordPress versions to fit your specific needs (see terms of service). While the Cloud version’s source code is not directly editable, it supports extensive customization via the JavaScript API, Web API, and custom CSS. Since the chat widget does not use an iframe, styling it with custom CSS is seamless and effective.

Hire Us

If you require specific customizations but lack the resources to implement them, our team is available for hire. We can tailor CHAT.devad.io to your exact requirements. Our hourly rate is 100 USD. To request a quote based on the complexity of your project, contact us via the support chat in the bottom right corner or email us at [email protected]. We typically reply within 24 hours.

This section contains help for This section contains help for Mobile App and other features not listed above.

The CHAT.devad.io admin area is a PWA, which means that you can install it on desktop, Mac, iPhone, or mobile devices and use it like a fully-functional app. Note: This feature is optimized for Google Chrome and Safari. The PWA is supported on all versions of CHAT.devad.io.

Enter in your admin area (e.g. https://chat.devad.io), and click the + icon on the top right of the URL bar of your Chrome browser. If you are using the WordPress version see the information below.

If you are using the cloud version of CHAT.devad.io on Android you can use the apps available on Google Play. We recommend using the PWA instead of the Android app to have the latest features and updates.

Google Play

• Enter in your admin area with Google Chrome (https://chat.devad.io/)
• Open your browser’s settings.
• Scroll down and tap Add to Home screen.
• Confirm by tapping Add.

• Enter in your admin area with Safari ( https://chat.devad.io/)
• Press the Share button and select Add to Home Screen from the popup.
• Tap Add in the top right corner to finish installing the PWA.

Admin area keyboard shortcuts are enabled on both PC and MAC and work as follows:

URL parameters allow the chat to perform specific actions on page load. To use them, append the URL parameters below to any URL on your website that displays the chat. Ex. https://example.com/?conversation=1234

URL parameters allow the administration area to perform specific actions on page load. To use them, append the URL parameters below to your admin URL. Ex. https://chat.devad.io/?conversation=1234.

?login_email=email&login_password=password

• You can enable the log file from Settings > Miscellaneous > Logs. This feature is not available in the cloud version.
• The log file is saved in the CHAT.devad.io installation directory.
• The logs record the following actions of agents and administrators: message sent, message deleted, conversation archived, conversation deleted, conversation restored, conversation assigned to an agent, conversation assigned to a department, user updated, user deleted.

Security is critical here at CHAT.devad.io. We work with security experts who perform periodic security audits. We continually implement the latest security technologies and stay up-to-date on the latest security threats. Find below some of the security measures that have been implemented in CHAT.devad.io.

CHAT.devad.io permits a maximum of 10 unsuccessful login attempts within an hour. In case the limit is exceeded by a user, admin, or agent, they will be unable to access their account or the admin area for a period of 1 hour. This blocking mechanism is based on the user’s IP address and serves to deter brute force attacks aimed at uncovering login credentials. If you encounter the “Too many login attempts. Please retry again in a few hours.” error, you have two options: either wait for a few hours or make changes to the CHAT.devad.io database by deleting the ip-ban row from the sb_settings table.

To prevent XSS injection protection attacks, all sensitive user inputs undergo sanitization.

To prevent CSRF attacks, all requests are validated by checking the login cookie and the client-side login string.

Whenever the password or the details for an admin or agent is changed, all active sessions are automatically logged out when sensitive operations are executed or after 1 hour.

We use 256-bit AES encryption to encrypt sensitive data such as active session login data.

CHAT.devad.io ensures that all uploads are renamed with a random alphanumeric string prepended to the original file name to prevent discovery of the URL and unauthorized download of the uploaded file. Kindly note that, for this feature to function properly, your server must prohibit directory listing.

CHAT.devad.io is one of the fastest support systems on the market. Its JavaScript and CSS file sizes are significantly smaller than those of most competitors, ensuring faster load times. Server-side performance is equally impressive. The system is extremely lightweight, built without frameworks or unnecessary code. It’s modular, minimal, and fully optimized for maximum performance. Nevertheless, you can further improve performance from Settings > Miscellaneous > Performance optimization. Below is a description of each available optimization setting.

• Minify JS: Enable loading of minified JavaScript and CSS files for the front-end chat widget to reduce file size and improve loading speed.
• Disable reports: Disable the reports area and stop recording report data. This prevents the system from consuming resources to collect and store report-related information.
• Disable articles: Disable the articles area and article functionality. This reduces resource usage by preventing the system from loading articles on both the admin and client sides.
• Archive old messages: Move messages older than the specified interval to a dedicated database backup table. Archived messages and their associated conversations will no longer appear in the admin or user conversation areas. However, if a user sends a new message in the future, the system will automatically restore the conversation and its message history. You can also manually access and restore archived conversations at any time by opening the user’s profile and selecting the archived conversation. Activate this feature if you handle a large volume of messages (in the millions). It will drastically improve performance.

You can fully edit the source code of CHAT.devad.io Web and WordPress versions. See the terms of service for more details. The cloud version source code is not editable, but you can customize it by using the JavaScript API and the Web API, or with JavaScript and CSS. The chat widget does not use an iframe, so you can easily customize it with JavaScript and CSS.

If you want us to customize CHAT.devad.io for you, please contact us and send us your requirements. We will provide you with a quote based on the complexity of the work. Our hourly rate is 25 USD. Contact us throught the chat here on the right bottom corner of the page or email us at [email protected]. We usually reply within 24 hours.

Notifications Management Overview

Understanding exactly when and how notifications are triggered is essential for maintaining smooth communication. If you suspect notifications aren’t functioning correctly, please review the logic below, as testing methods often differ from real-world usage scenarios.

Email Notifications System

Both support agents and end-users can receive email alerts whenever a new message lands in their inbox. This ensures that no critical communication is missed, even when users are offline.

For Admins and Agents

When a user sends their very first message, the system intelligently routes the notification based on assignment rules:

• Department Assignment: If the chat is routed to a specific department, only agents within that department receive the email.
• Specific Agent Assignment: If assigned to a particular individual, only that agent is notified.
• Unassigned: If neither applies, an email is broadcast to all agents who are currently offline.

For subsequent messages in an ongoing conversation, emails are sent exclusively to the last agent handling the chat, provided they are currently offline. If the Human Takeover feature is active within the Artificial Intelligence app, the system suppresses notifications if the chatbot successfully answers the query.

For Users

Users receive email notifications only when an agent replies and the user is currently offline. To prevent inbox spam, only one email alert is sent per offline session; subsequent messages will not trigger additional alerts until the user returns.

Customizing Email Templates

You can fully customize the content of these emails via Settings > Notifications. The editor supports both plain text and HTML. New lines are automatically converted to HTML line breaks. Use the following dynamic merge fields to personalize your messages:

Optimization via Cron Jobs

For a more robust notification system, you can offload email sending to a cron job. This is highly recommended as it improves performance and ensures emails include the entire conversation context.

Use the following command format, replacing [SCRIPT-URL] with your actual Installation URL found in Settings > Miscellaneous:

*/59 * * * * wget [SCRIPT-URL]/include/api.php?email-notifications=true

Troubleshooting Email Delivery

Real-Time Push Notifications

Unlike standard desktop notifications, Push notifications are delivered from a server even when the user’s browser is closed or the device is offline. We support both Pusher (Android/Desktop) and OneSignal (iOS/Android/Desktop). Note that iOS devices strictly require OneSignal.

Setup: OneSignal (iOS Support)

For Apple devices (iOS 16.4+), you must use OneSignal. The setup involves creating a Web Configuration in OneSignal, entering your site’s root domain, and uploading the required SDK files (sw.js etc.) to your server’s root directory.

• Cloud Version: OneSignal is pre-configured by default.
• WordPress: You must access the chat admin area directly (outside the WP dashboard) to finalize push settings.
• Service Workers: You need to define the path to your service worker files in the settings if they are not in the root.

Additional Notification Types

Desktop Notifications

These are standard browser notifications. They work only over HTTPS and are not supported on iOS. If Push notifications are active, they will override and replace standard desktop notifications.

SMS Notifications (Twilio)

You can send SMS alerts to both agents and users via Twilio integration. This also enables a true two-way texting experience where SMS replies appear in the chat.

• Setup: Enter your Twilio SID, Auth Token, and Phone Number in Settings > Notifications > Text message notifications.
• Sender ID: You can replace the phone number with a custom Sender Name (Alphanumeric Sender ID) where supported.
• Logic: SMS notifications are sent only if the recipient is offline. They are disabled if the AI chatbot successfully handles the query.

Sound Alerts

Audio alerts play when a new message arrives. Due to browser security policies, sound will only play if the user has interacted with the document (clicked somewhere on the page). If set to loop, the sound plays until the chat window is opened or maximized.

Conversations have a total of four different statuses: mark as read, archive, delete and restore. You can manage the status of a conversation by opening it in the conversations area and then clicking any of the corresponding icon buttons in the top right of the conversation window.

You can for conversations by department ID, assigned agent ID, conversation title, conversation ID, message text, message attachments name, user first name, user last name, user email. If you search for a specific message text, the conversation containing that message will be shown at the correct position and the message will be highlighted.

• When you empty the trash, all the conversations in the trash are permanently deleted.
• When a user sends a new message to an archived or trashed conversation, the conversation is automatically restored and will now be visible in the Inbox area.
• Trashed conversations are deleted automatically after 30 days.
• When a user is deleted, all the conversations and messages are permanently deleted too.
• An agent can delete their messages by opening the message menu and clicking Delete. The message menu becomes visible when you hover the mouse cursor over the message.
• The left conversations list use auto-pagination, which is limited to 100 results per scroll.

You can reply to a message by opening the message’s menu and, and clicking Reply to. The reply to feature is supported only on the following messaging services: WhatsApp, Telegram, Facebook Messenger.

The text editor of the admin area and automated messages(example: welcome and subscribe messages) can be used to create stylized messages:

• Links formatting — All text links are automatically converted to clickable hyperlinks. To set the link name, append the following string to the URL: #sb-example. Replace example with your desired link name and white spaces with —.
• Text formatting — The editor also supports text formatting syntax:
  • To make text bold, surround it with *: *your text*.
  • To make text italic, surround it with __: __your text__.
  • To make text strikethrough, surround it with ~: ~your text~.
  • To insert a single-line code comment, surround it with`: `your text`.
  • To insert a code block, surround it with “`: “`your text“`.

Merge fields are strings replaced by external values when used. Merge fields can be used in any message or automated message, including chatbot messages.

Rich messages are special messages with interactive features like buttons, dropdowns, or inputs. They allow an agent to request information from the user via a user input form or to diplay interactive contents. Rich messages can be inserted into a chat message using shortcodes. Shortcodes accept various parameters like title and description. The available rich messages are listed below.

If your text includes the characters ,, :, or “, you must prepend the character to them. For example: ,, :, “.

All of the rich messages support the following parameters:

You have to create a Dialogflow chatbot, then simply enter the rich message shortcode into the text response of the Intent.

When a user completes a rich message, the response data is saved in JSON format in the database under table sb_messages and column payload. Example:

To translate a rich message string, the original rich message text must be in english, add the exact english text and its translations in Setting > Translations > Front End.

To display a rich message, such as a list of buttons, when a user initiates a chat for the first time, insert the rich message shortcode into the welcome message.

You can create custom rich messages with your own custom content by going to Settings > Miscellaneous. Currently, custom rich messages are static and there are no interactive options available as there are with shortcodes. However, you can insert custom HTML codes.

When creating a custom rich message, you can use the following codes:

The built-in messages are pre-programmed messages sent automatically by CHAT.devad.io. You can find them by going to Settings > Messages.

Send a message to new users when they visit the website for the first time.

• Text formatting is supported.
• Merge fields are supported.
• Rich messages are supported.
• The welcome message is not sent to slack.
• Conversations containing only the welcome message (and no response) are automatically archived.

If no agents respond within the specified time interval, a message will be sent to request the user’s details, such as their email.

• Text formatting is supported.
• Merge fields are supported.
• You can send a confirmation email to the user by filling in the Follow-up Email fields.
• If the delay is not set, a dynamic time interval is utilized and it is determined as follows: If Settings > Miscellaneous > Office hours is configured, and the current time falls within the defined office hours, or if at least one agent is online, then the delay will be set to 15 seconds. In all other cases, the delay will be set to 5 seconds.
• Follow-up messages are sent a maximum of once every 24 hours.
• If the user provides an email address and the newsletter feature is enabled, the email address will be subscribed.
• The follow-up message is sent only to users without email address.
• If the chatbot’s human takeover feature is activated, the follow-up message is only sent during human takeover.

Display the feedback form to rate the conversation when it is archived.

• The rating message is compatible with the messaging channels. The rating buttons are not displayed on messaging channels. However, if Artificial Intelligence and OpenAI are set up, the user’s reply will be analyzed to extract the rating.
• The rating is visible in the right panel of the conversations area, in the agent ratings report of the reports area, and in the agent profile.
• Enable the rating email reminder by setting the delay (in hours) in the Email reminder delay option. The email remind the user to provide a feedback and it is sent only if the user hasn’t rated the conversation after the set delay. For this feature to work, you must also set the Redirect URL — enter any URL that includes the chat widget (e.g., your website URL). Once the user clicks the Helpful or Not helpful link in the email, they will be redirected to the specified Redirect URL, and the rating will be saved automatically. The chat will open showing the rating panel, allowing the user to provide additional feedback.
• The emails are sent through the cron jobs.

Notify the user when their message is sent outside of the scheduled office hours or all agents are offline.

• Text formatting is supported.
• Merge fields are supported.
• To learn more about the office hours option, please click here.
• The offline message is sent to the same user maximum 1 time per hour.
• By default, the offline message is also sent if all agents are offline, even during office hours. To prevent this, enable the Disable agents check option.
• If the chatbot’s human takeover feature is activated, the offline message is only sent during human takeover.
• If you or any other agent is online using Slack, they will be considered as online agents also by CHAT.devad.io.

Present a privacy message accompanied by Accept and Decline buttons. The user’s approval by clicking on the Accept button is required to start using the chat. This feature ensures privacy policy enforcement and GDPR compliance.

• The privacy message is not shown if the Settings > Users > Require registration option is enabled.
• The privacy message is also sent to messaging channels like WhatsApp, but the user does not have the option to approve or decline the privacy policy. The messaging functionalities are not blocked either. The message is sent after the user initiates the conversation by sending their first message.

Show a pop-up notification to all users.

• The popup message is always shown until the user manually closes it; then it stays closed.

Here, you can access information regarding the uploading of files and the message’s attachments.

• The following image formats are displayed automatically:.jpg, .jpeg, .png.
• For instructions on sending attachments with a chatbot, click here.
• You can also upload files to AWS S3.

Here, you can access information regarding a variety of features associated with conversations.