Skip to main content
The Chat Configuration page (found under Channels > Chat in the sidebar) controls whether your agent responds to chat messages and how it behaves in chat conversations.
To create a chat widget and complete setup, go to Widget.

​
General

Select the language model that powers your chat agent.
​
Large language model
dropdown
Choose the LLM for chat responses.Example: GPT-4o mini

​
Style prompt

Use this prompt to tailor tone, format, and etiquette specifically for the chat channel.
​
Style prompt
string
An optional multiline prompt that adjusts how your agent responds in chat. Use this to set channel-specific formatting or communication style that differs from voice.Example: “Use concise responses with bullet points. Include links when helpful.”
The style prompt is optional. If left empty, the agent uses its default persona across all channels.

​
Greeting

Configure what your agent says when a chat session begins.
​
Greeting message
string
The first message your agent sends when a user opens the chat widget.Example: “Hello, how can I help?”
Keep your greeting short and welcoming. Avoid long introductions that push the conversation off-screen.

​
Safety filters

Enable channel-specific content safety filters to control what responses are allowed in chat.
​
Enable safety filters
boolean
When enabled, applies content filtering to chat responses. When disabled, defaults are managed under Configure > General.
These filters apply to the chat channel only. Voice channel safety settings are configured separately.
When safety filters are enabled, adjust the strictness for each category using the sliders:
CategoryDescription
ViolenceControls filtering of violent content (Lenient → Strict)
HateControls filtering of hateful or discriminatory content (Lenient → Strict)
Sexual contentControls filtering of sexually explicit content (Lenient → Strict)
Self-harmControls filtering of self-harm related content (Lenient → Strict)
More lenient settings allow a wider range of content through. Review your use case and compliance requirements when adjusting these settings.

​
Branching behavior

Chat configuration aligns with environment branching. Changes made in Sandbox can be promoted to Pre-release and Live environments, ensuring consistent testing and deployment workflows.

​
Markdown support

Chat messages support formatted markdown rendering:
  • Bold and italics
  • Bulleted and numbered lists
  • Links
  • Code blocks
Formatted markdown appears in both the Test Agent Chat panel and Conversation Review.

​
Next steps

After configuring chat settings:
  1. Configure the widget - Style and customize the chat widget appearance
  2. Deploy to your website - Generate and embed the script tag
You must configure chat settings before the widget will function. In-product banners will guide you through this process.