> For the complete documentation index, see [llms.txt](https://docs.patagon.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.patagon.ai/en/agent-optimization/agent-feedback.md).

# How to give feedback to your agent

Feedback teaches your agent what a good or bad response looks like in your specific context. You give it message by message, directly in the conversation view.

1. In the sidebar, go to Leads > Conversations.
2. Open any completed or active conversation.
3. Find a message sent by the agent.
4. Click the Leave Feedback button that appears below that message.
5. Mark the response as correct or incorrect and add a note if needed.

![Agent feedback](/files/5Ok9hxA8S6Iwy06gr6l2)

The most valuable feedback comes from messages where the agent said something that lost the lead's interest, asked the wrong question, or gave an incomplete answer.

{% hint style="warning" %}
Feedback works at the message level, not the conversation level. Review the full conversation before deciding which specific messages to flag.
{% endhint %}

You can also review completed conversations from Agent > Conversation Feedback in the sidebar, which shows the full list filtered by Completed or Active status.

After giving feedback on at least 10–15 conversations, check your qualification rate in the Dashboard to see if scoring accuracy is improving.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.patagon.ai/en/agent-optimization/agent-feedback.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.