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
The text editor of the admin area and automated messages(example: welcome and subscribe messages) can be used to create stylized messages:
Merge fields are strings replaced by external values when used. Merge fields can be used in any message or automated message, including chatbot messages.
| Code | Description |
|---|---|
|
{user_name}
|
Full name of the active user.
|
|
{user_email}
|
Email of the active user.
|
|
{agent_name}
|
Full name of the active agent.
|
|
{agent_email}
|
Email of the active agent.
|
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.
Create a rich message by inserting the shortcode into the text editor of the admin area. Customize all of the parameters with your information and send your message.
When a shortcode is used, the user sees the rich message (not the shortcode) and can select or enter the required information to complete the form submission.
Once the rich message form has been filled out and sent by the user, a success message is shown and the form data is saved.
| Name | Shortcode | Description |
|---|---|---|
|
Card |
[card image="URL" header="TITLE" description="Lorem ipsum dolor sit amete" link="URL" link-text="Purchase" extra="$599" target="_blank"] |
Call-to-action card with an image, title, description, link, and more.
|
|
Slider |
[slider image-1="URL" header-1="TITLE" description-1="Lorem ipsum dolor sit amete" link-1="URL" link-text-1="Purchase" extra-1="$599" image-2="URL" header-2="TITLE" description-2="Lorem ipsum dolor sit amete" link-2="URL" link-text-2="Purchase" extra-2="$599" target="_blank"] |
Slider of call-to-action cards with an image, title, description, link, and more. You can add up to 10 slides.
|
|
Slider images
|
[slider-images images="URL,URL,URL"] |
Slider of images.
|
|
Chips |
[chips options="A,B,C"]
|
List of buttons. |
|
Buttons |
[buttons options="A,B,C"] |
List of buttons.
|
|
Select |
[select options="A,B,C"]
|
Dropdown list of options.
|
|
Inputs |
[inputs values="A,B,C" button="Send now"]
|
List of text inputs.
|
|
Email |
[email name="true" last-name="true" phone="true" phone-required="false" placeholder=""]
|
Form to collect the user's email and phone number. All attributes are optional. Follow up settings used as default values. Add the attribute required-messaging-apps="true" to force users to provide their email and phone on messaging apps. Merge fields are supported. |
|
Timetable |
[timetable]
|
Timetable.
|
|
Articles |
[articles link="https://chatloop.io/articles-demo"] |
Articles with search area. The link attribute is used as fallback message for Facebook Messenger, WhatsApp, Telegram messages. |
|
List |
[list values="A,B,- C,- D,E" numeric="true"]
|
Text list. Prefix an item with the - char to make it an inner item.
|
|
List double
|
[list values="A:X,B:Y,C:Z"]
|
Text list with titles.
|
|
List image
|
[list-image values="URL:A,URL:B,URL:C"]
|
Text list with titles and images.
|
|
Table |
[table header="A,B,C" values="A:B:C,A:B:C,A:B:C"]
|
Table. |
|
Button |
[button link="https://chatloop.io" name="Click here" target="_blank" style="link"]
|
Display a link or open an article. The attribute target="_blank" is optional and open the link in a new window. The attribute style="link" is optional and change the button design. To open an article on click the link value must be #article-ID, replace ID with the article ID. |
|
Video |
|
Display a YouTube or Vimeo video. The value of the attribute type can be youtube or vimeo. The attribute id is the ID of the video, get it from the URL. The attribute height is optional and sets the video height in px.
|
|
Image |
[image url="https://chatloop.io/wp-content/uploads/2025/02/admin.png"]
|
Image. |
|
Share |
[share fb="https://chatloop.io/" tw="https://chatloop.io/" li="https://chatloop.io/" pi="chatloop.io/" wa="https://chatloop.io/"]
|
Social share buttons.
|
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:
| Parameters | Description |
|---|---|
|
id="123"
|
The ID of the rich message (used also to save the JSON data).
|
|
title="ABC"
|
The rich message title.
|
|
message="ABC"
|
The rich message description that appears underneath the title.
|
|
success="ABC"
|
The message that appears when the user completes and sends the rich message. The user input is appended to this message.
|
|
settings="ABC"
|
Extra field for optional extra values.
|
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:
{"rich-messages":{"4Voyu":{"type":"email","result":{"email":["[email protected]","Your email..."]}}}}
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:
| Code | Description |
|---|---|
|
<a href="https://www.google.com" target="_blank" class="sb-rich-btn sb-btn">Click here</a>
|
Link with button design.
|
|
<a href="https://www.google.com" target="_blank" class="sb-rich-btn sb-btn-text">Click here</a>
|
Link.
|
|
<div class="sb-image"><img src="https://via.placeholder.com/1500x600" class="sb-image" /></div>
|
Image that zoom on click.
|
The built-in messages are pre-programmed messages sent automatically by Chatloop. You can find them by going to Settings > Messages.
Send a message to new users when they visit the website for the first time.
If no agents respond within the specified time interval, a message will be sent to request the user’s details, such as their email.
Display the feedback form to rate the conversation when it is archived.
Notify the user when their message is sent outside of the scheduled office hours or all agents are offline.
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.
Show a pop-up notification to all users.
Here, you can access information regarding the uploading of files and the message’s attachments.
Here, you can access information regarding a variety of features associated with conversations.
Tags enable more efficient organization and grouping of conversations. Please refer to the information below for further details.
Notes allow users to add comments to conversations that are only visible to agents and admins.
The full conversation can be sent to the user by the agent or admin as a transcript file.
Manage users from the Users area in the left menu of the admin area.
You can import users from Settings > Users > Import users. Only CSV files are supported. You can download an example CSV file here. In the example file, the first row is the header and the columns Height and Hair color are custom user fields added from Settings > Users > Custom fields.
You can search users by name, surname, email, and custom fields.
You can delete a user by opening the User edit box and then clicking Delete user. To delete multiple users at once, select the users you want to delete from the Users table and then click the top right Delete icon.
To display additional columns in the user table go to Settings > Admin > Users table additional columns and add the new columns. The value of each column is the slug of the user detail or extra user detail you want to display. The slug is lowercase and with spaces replaced by the char –. For example, the slug of the extra user detail “Date of birth” is “date-of-birth”.
| Type | Description |
|---|---|
|
user |
A "user" is any user with an email.
|
|
lead |
A "lead" is any user with no user details, who is automatically registered, and with at least one conversation.
|
|
visitor
|
A "visitor" is any user who has not started a conversation. Note: Visitors are automatically deleted every 24 hours.
|
Manage, create, and delete agents and admins from the Users area.
You can gather user details, such as their name and email, through various methods:
The registration form is a pre-chat form that requires the user to enter specific information before starting the chat.
You can assign an agent to a conversation in several ways:
You can set the office hours timetable from Settings > Miscellaneous > Office hours. Office hours are used for:
Knowledge base articles provide instant answers to customers to help reduce customer support volume. You can access the articles from the Chatloop menu.
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.
You can enable the URL rewrite from Settings Articles > URL rewrite. The default URLs of Chatloop are not user-friendly and they include parameters. You can rewrite the URLs via .htaccess file. The code below rewrites the URLs of the categories and article pages. The categories URL changes from articles.php?categories=ID to articles/category/ID. The article URL changes from articles.php?article_id=ID to articles/ID.
<IfModule mod_rewrite.c> RewriteEngine On RewriteRule ^articles?$ articles.php [L] RewriteRule ^articles/category/(.*)$/?$ articles.php?category=$1 [L,QSA] RewriteRule ^articles/(.*)$/?$ articles.php?article_id=$1 [L,QSA] </IfModule>
Change articles with the name of your articles page and set the articles page URL in Settings > Articles > Articles page URL.
Chatloop is fully multilingual and provides powerful features to detect the user’s language on the fly.
To edit the languages of both chat and admin, go to Settings > Translations. Some settings, such as e-mail contents, are directly translatable and therefore do not need to be translated here.
Chatloop is already translated into 41 languages. There are many options available to set the language:
You can translate almost any custom content like rich messages, titles, descriptions, automatic messages, chat header, and more. To include translations, visit Settings > Translations and click on the New translation button. Then, enter the English content you wish to translate in the first field and its corresponding translation in the second field. The original text must be in English. If you have the artificial intelligence app you can also translate all contents to any language automatically through the multilingual via translation feature.
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:
You can assign a department to a conversation in several ways:
Email piping lets you, your agents, and your users reply to chat messages via email.
To activate the email piping go to Settings > Notifications > Email piping and enter your POP3/IMAP email server information, then set the email address to use for the email piping in Settings > Notifications > SMTP and you’re done! The email address must be the one to which the email piping server connects to. Chatloop will send all emails from this email address and you, your agents, and your users will reply to this email address.
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.
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.
Automations allow running multilingual automatic tasks when conditions set by you are met.
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.
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.
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.
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.
| Code | Description |
|---|---|
|
{recipient_name}
|
The name of the user or agent who is receiving the email.
|
|
{sender_name}
|
The name of the user or agent who was sending the message that triggered the email notification.
|
|
{sender_profile_image}
|
The profile image of the user or agent who was sending the message that triggered the email notification.
|
|
{message}
|
The links to any attachments that were part of the message that triggered the email notification.
|
|
{attachments}
|
Emails may not be delivered for several reasons; below are the most common ones:
|
Emails may not be delivered several reasons; below are the most common ones:
| Reason | Description | Solution |
|---|---|---|
|
Hosting problems |
The email server of your web hosting provider is not able to send emails or the emails are sent but they are automatically detected as spam and deleted by the email clients. |
If the settings at Settings > Notifications > SMTP are not set, your server will send the emails instead. Contact your web hosting provider regarding email support or use your SMTP server by activating it in Settings > Notifications > SMTP.
|
|
SMTP problems |
The email is not sent also if you activated the SMTP option in the Notifications area. |
If you don't receive the emails make sure they are working by sending a test email from Settings > Notifications > Send a user email notification or Send an agent email notification. If you don't receive the test email, your SMTP server, is not working. Open the browser console for more details about the error. Because this is not an issue related to Support Board , the support doesn't cover it, please contact your server/hosting/SMTP support instead. You can use sendgrid.com, you can send 40000 emails for 30 days for free, then 100/day forever for free.
|
|
Google Gmail |
The email is not sent also if you activated the SMTP option in the Notifications area and you are trying to the Gmail SMTP server. |
If you're using Gmail enter smtp.gmail.com as host and set 465 or 587 as port. You need also to allow access to Gmail to less secure apps, you can do it from https://myaccount.google.com/lesssecureapps.
|
Push notifications are like Desktop notifications but with some key difference. Desktop notifications, also called Web notifications, are requested directly by the client while Push notifications come from a server. The main difference is that the Push notifications work always, also if your device is offline, or Chatloop is not open. Also, they are persistent and always visible until closed. Push notifications require an external service to work. We support Pusher and OneSignal, they are free to use for up to 2000 users/devices. Pusher does not support iOS devices. You need to use OneSignal if you have an iOS device.
The cloud version of Support Board uses OneSignal by default, you do not have the option to configure it. For the admin area everything is already configured and you only have to check the Settings > Notifications > Push notifications > Active for agents option, save the changes, and reload the admin area.
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.
The settings below are related to the Artificial Intelligence app.
The human takeover happens in these cases:
When the option Human takeover is active the following happens:
When the user confirms the human takeover, or if it is automatic, the following happens:
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": [] } }
The make the human takeover request work on WhatsApp, Messenger, Telegram and the other messaging apps, you need to create a new Intent with human-takeover as input Context, nothing as output Context, a list of the user’s most common confirmation messages as Training phrases(e.g. ok, yes) and { “human-takeover”: true } as Custom Payload response .
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.
Chatloop provides powerful tools to assist you in the process of creating the chatbot.
You can open the chatbot training window from the conversation area by hovering the mouse over a message, opening the message’s menu, and selecting Train chatbot.
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 Support Board chat, and an error should appear in the console. On Chrome you can open the console from Settings > More tools > Developer tools > Console.
The settings below are related to the Artificial Intelligence app.
The human takeover happens in these cases:
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.
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.
This features allow you to use your own Assistants created at https://platform.openai.com/assistants.
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. Support Board 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.
When this option is active, audio messages will be converted to written text.
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.
Chatloop 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 window.
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.
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.
This training process enables you to train the chatbot using websites.
This training process enables you to train the chatbot by adding questions and answers individually.
This training process enables you to train the chatbot using the articles.
This training process enables you to train the chatbot using the flows.
This training process enables you to train the chatbot using the conversations from the users and agents.
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.
This feature allow the chatbot to answers to questions that require real-time information, such as, “What is the temperature in London today?”.
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.
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.
Function calling allows you to connect the chatbot to external tools and systems. The chatbot will query your server and return the information from your server to the user. 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.
Your server must returns a JSON array with the values required by the chatbot. E.g. [“order_status” => “Delivered 2 hours and 25 minutes ago”].
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.
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.
The settings below are related to the Artificial Intelligence app.
This feature is available only on the cloud version of Chatloop
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.
This features allow you to use your own Assistants created at https://platform.openai.com/assistants.
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. Support Board 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.
When this option is active, audio messages will be converted to written text.
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.
Chatloop 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 window.
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.
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.
This training process enables you to train the chatbot using websites.
This training process enables you to train the chatbot by adding questions and answers individually.
This training process enables you to train the chatbot using the articles.
This training process enables you to train the chatbot using the flows.
This training process enables you to train the chatbot using the conversations from the users and agents.
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.
This feature allow the chatbot to answers to questions that require real-time information, such as, “What is the temperature in London today?”.
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.
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.
Function calling allows you to connect the chatbot to external tools and systems. The chatbot will query your server and return the information from your server to the user. 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.
Your server must returns a JSON array with the values required by the chatbot. E.g. [“order_status” => “Delivered 2 hours and 25 minutes ago”].
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.
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.
