> For the complete documentation index, see [llms.txt](https://docs.material.security/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.material.security/learn-more/administration/security/openai.md).

# OpenAI

### Overview <a href="#h-overview" id="h-overview"></a>

{% hint style="warning" %}
Material AI is a beta feature.
{% endhint %}

By default, Material AI features are powered by AI models running within your Material tenant - no data leaves the Google Cloud Project where your Material instance is deployed. Various AI models can differ in performance, so if you would prefer to use OpenAI’s GPT models to power Material AI, please speak to your customer success representative.

Material Security regularly adds new functionality and capabilities to Material AI. When OpenAI is enabled, data is sent to OpenAI under the following circumstances:

* To perform User Report analysis in the Phishing Protection product, message headers and selected body content will be sent to OpenAI.
* To provide explanations of what various message headers mean, those headers will be sent to OpenAI.

This list of use cases is subject to change at any time.


---

# 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.material.security/learn-more/administration/security/openai.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.