> ## Documentation Index
> Fetch the complete documentation index at: https://docs.poly.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Configuration

> Configure LLM, greeting, and safety filters for chat.

<img src="https://mintcdn.com/polyai/UsUlibhFFP5HoWRL/images/webchat/config.png?fit=max&auto=format&n=UsUlibhFFP5HoWRL&q=85&s=b9ef0f5cca30eb7e7f11151e4888ee8e" alt="chat-configuration" width="3020" height="1614" data-path="images/webchat/config.png" />

Configure chat settings in **Channels > Chat**. Create widgets at **[Widget](/widgets/configure)**.

## General

Select the language model that powers your chat agent.

<ParamField path="Large language model" type="dropdown">
  Choose the LLM for chat responses. Available models include PolyAI's **Raven 3.5** (recommended), OpenAI (GPT series), and Amazon Bedrock options.
</ParamField>

**Recommended for chat:** PolyAI's [Raven 3.5](/agent-settings/raven) is designed for conversational AI and tuned for both voice and chat. It supports custom style instructions, auto-reasoning for complex queries, out-of-domain detection, and 24+ languages. [Raven V3](/agent-settings/raven) is optimized for voice only and can only be selected in [Voice configuration](/voice/voice-configuration) — **Raven 3.5** extends all Raven capabilities to chat.

## Style prompt

Use this prompt to tailor tone, format, and etiquette specifically for the chat channel.

<ParamField path="Style prompt" type="string" optional>
  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."
</ParamField>

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.

<ParamField path="Greeting message" type="string">
  The first message your agent sends when a user opens the chat widget.

  **Example:** "Hello, how can I help?"
</ParamField>

Keep your greeting short and welcoming. Avoid long introductions that push the conversation off-screen.

## Safety filters

Safety filters are configured on a **per-channel basis**. The chat channel has its own safety filter settings, separate from the voice channel and the project-wide defaults.

<ParamField path="Enable safety filters" type="boolean">
  When enabled, applies content filtering to chat responses. These filters apply to the chat channel only. Default settings can be managed on the **Configure > General** page.
</ParamField>

When safety filters are enabled, adjust the strictness for each category using the sliders:

| Category           | Description                                                                |
| ------------------ | -------------------------------------------------------------------------- |
| **Violence**       | Controls filtering of violent content (Lenient → Strict)                   |
| **Hate**           | Controls filtering of hateful or discriminatory content (Lenient → Strict) |
| **Sexual content** | Controls filtering of sexually explicit content (Lenient → Strict)         |
| **Self-harm**      | Controls filtering of self-harm related content (Lenient → Strict)         |

The jailbreak attack filter is always enabled and cannot be turned off.

<Warning>
  More lenient settings allow a wider range of content through. Review your use case and compliance requirements when adjusting these settings.
</Warning>

## Branching behavior

Chat configuration changes take effect immediately when saved. Unlike other project settings, webchat does not follow the environment branching system – there is no Sandbox, Pre-release, or Live promotion step. Use the **Test Agent Chat** panel to verify changes before saving.

## Markdown support

Chat messages support formatted markdown rendering:

* **Bold** and *italics*
* Bulleted and numbered lists
* [Links](https://example.com)
* `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](/widgets/configure)** - Style and customize the chat widget appearance
2. **[Deploy to your website](/widgets/configure#embed-tab)** - 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.