Settings
General
This tab shows the Chatbot ID, the number of characters, the name of the chatbot, the credit limit, delete chatbot and delete conversations.
The Credit Limit is activated when you want to set the maximum limit of credits to be used by this chatbot from the credits available on the team.
DANGER ZONE
The actions done in the section aren’t reversible. If you deleted the chatbot or the conversations, you can’t retrieve them moving forward.
AI
This is the most important section when it comes to the behavior of the chatbot and how it answers the users’ questions.
This section contains the model of the LLM, the instructions prompt, the temperature of the AI, and the auto training.
Model
You can choose the model you want the chatbot to use when it answers the users. OpenAI, Claude and Gemini are available to be used.
Instructions
This section is important to set the behavior of the chatbot when it answers the questions of the users. The instructions prompt should include some text to describe to the chatbot how to answer specific questions, what to do when the answer isn’t provided in the sources, when to provide URLs.
You should add that the chatbot should rely on the sources when answering the questions, and not to answer any question not mentioned in the training data to avoid providing misleading information.
The instructions added allow you to customize your chatbot’s personality and style. Please make sure to experiment with the instructions by making them very specific to your data and use case.
The instructions area has an option to add a custom prompt or a pre-defined example of instructions
Temperature
The temperature is adjusted based on how creative you want your chatbot to be while answering the questions. It’s recommended to set the temperature on 0.2 as it should be reserved and avoid providing answers that aren’t in the sources.
Chat Interface
This section allows you to adjust the chat interface, where the bubble should appear, the welcome message, and chat icon.
- Initial message: The message shown once the user opens the chat bubble.
- Suggested messages: The messages that the users can use when contacting the chatbot. This should be the most frequently asked questions by the users.
- Text placeholder: The text shown in the field where the users write their questions.
- Collect feedback: When enabled, it allows the user to provide a feedback by displaying a thumbs up or down button on chatbot messages.
- Regenerate messages: Display a regenerate response button on chatbot messages.
- Footer: Text shown in the button of the chat. You can use this to add a disclaimer or a link to your privacy policy.
- Theme: Light or Dark
- Display Name: The name of the chatbot appearing to users.
- Profile picture: Picture of the chatbot when providing answers.
- Chat Icon: The icon appearing on the website to display the chatbot.
- User message color.
- Align Chat Bubble Button: Left or Right
- Auto show initial messages pop-ups after: You can set it to negative to disable.
Leads
This page is responsible for collecting Lead information from your users. This form appears after the first response generated by the bot.
You can configure a combination of the three fields (Name, Email, Phone number). You can also configure the message that shows on top of the Lead form from this page, along with the label for each of the collected fields.
This form is optional so your user can choose to not fill it and will continue receiving responses from the bot. You can also configure more advanced behavior for the lead form using the Actions tab.
This is how the lead form appears in the chat :
Notifications
From this page, you can configure the notifications you get from the bot. You can either opt for getting one email per day that contains all the leads submitted for that day. You can also opt for another email that sends you a daily email with the conversations done on that day.
You can add multiple email addresses to receive these emails if needed
Webhooks
On this page, you can configure a webhook to trigger based on a selected action.
Currently, the available action is “lead submitted.” When a new lead is submitted through your bot’s lead form, our system automatically triggers the webhook.
The webhook sends a POST request to your chosen API, including the conversation ID and lead form data (name, email, and phone number).
You can use this to automate workflows with third-party tools by capturing the webhook and using it to send messages or perform other actions.