> For the complete documentation index, see [llms.txt](https://docs.skyone.cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.skyone.cloud/english/experts.md).

# Experts

An **Expert** is a custom assistant: you define what it does, which model it uses, which instructions it follows, and which tools it can access.

### Create an Expert <a href="#create-an-expert" id="create-an-expert"></a>

To create a new Expert, follow these steps:

1. In the left sidebar, click **Experts**.
2. Open **Create new Expert**.
3. Click the **+** icon to choose an image for the Expert.
4. Fill in the **Expert name** and **What this Expert does** fields.
5. In the **Model** field, select the AI model the Expert will use.
6. In the **Category** field, choose the Expert's area. The default is **General**.
7. In the **Instructions** field, write the system instructions the Expert should follow. Click the expand icon to edit the text in full screen.
8. Under **Tools**, click **+ Add** to give the Expert access to tools.
9. Save the Expert.

{% hint style="info" %}
The **Model** and **Category** fields are required.
{% endhint %}

### Expert fields <a href="#expert-fields" id="expert-fields"></a>

* **Expert name:** how the Expert appears to users.
* **What this Expert does:** a short description of the Expert's role.
* **Model:** the AI model used for responses.
* **Category:** the area where the Expert is listed, such as **General**.
* **Instructions:** system instructions, such as tone, rules, and response format.
* **Tools:** additional capabilities the Expert can use (Examples: Google Calendar, OpenWeather, Calculator, etc).


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.skyone.cloud/english/experts.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.