> 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/objectives-and-tone.md).

# How to set your agent's objectives and tone

The Goals & Tone page is where you write your agent's full behavior prompt. Everything your agent says and does in a conversation comes from what you write here.

In the sidebar, go to Agent > General and click the Goals & Tone tab.

![Goals & Tone tab](/files/xTjZNq58QiJPKS5exjlf)

The page has a single code editor that contains your agent's prompt. This is a free-text field — there are no separate form fields. Everything is written in one place as a structured prompt.

## How to edit your prompt

1. Click anywhere in the editor to start editing.
2. Write or update your agent's prompt directly in the editor.
3. Use the Dark Mode toggle if you prefer a dark background while editing.
4. Click Save when you're done.

To preview how your agent responds before saving, click the panel icon next to Save. This opens an Agent Preview panel where you can send test messages.

{% hint style="warning" %}
There is no autosave. If you close the tab or navigate away before clicking Save, your changes will be lost.
{% endhint %}

Every time you save changes to your prompt, create a Draft version from the Versions tab to keep a snapshot of your work. See How to manage agent versions below.


---

# 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/objectives-and-tone.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.