# Chat Rules

Training Chat involves defining specific rules or conditions that trigger particular responses from the AI agent. This process ensures that the AI agent can provide structured and conditional responses based on user interactions. By specifying conditions and instructions, users can train the AI agent to follow these rules and produce the desired output in conversations.

**Steps to Train the AI Agent for Chat:**

1. **Input Condition:**  Define the conditions that must be met for the AI agent to use a particular response.
2. **Input Instruction:**  Define how the AI agent should respond during specific scenarios or interactions.
3. **Add Training:** Click the "Save" button to add  training cards.

<figure><img src="https://4292326968-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FqsAGx1GJXq13bQhP2sY7%2Fuploads%2FlH5lrJ4x0pQsvyL90GxB%2Fimage.png?alt=media&#x26;token=a80770b5-22f5-428d-9094-94dc0b1d5485" alt="" width="293"><figcaption><p>Training by Chat</p></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.feedloop.ai/agent-settings/training/chat-rules.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.