# Configuring your Mentors

You can configure the way your Mentor talks to users in different ways. For one thing, there's the content itself. Of course, the mentor is powered by state-of-the-art LLMs, so it has substantial knowledge out of the box, but we try to focus the mentor on your material.

During document ingestion, we will not only analyze the content, but more importantly also your writing style.

<figure><img src="https://gitbookio.github.io/onboarding-template-images/images-hero.png" alt=""><figcaption><p>Add alt text and captions to your images</p></figcaption></figure>

{% hint style="info" %}
At any time, you can change the writing style. But be careful, we are not timid with our settings. The mentors can get extremely direct and sassy.
{% endhint %}


---

# 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://mentormode.gitbook.io/mentormode-docs/basics/images-and-media.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.