> For the complete documentation index, see [llms.txt](https://docs.bsure.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bsure.io/user-guides/settings/system/ai-chat.md).

# AI Chat

## What AI Chat is

AI Chat lets you ask questions about your Microsoft 365 and Entra ID environment in plain language. AI Chat has **no built-in model**. You connect your own provider, and Bsure uses your credentials to send each question, with the supporting context it assembles, to that provider and return the answer inside the app.

This is a **bring-your-own-key (BYOK)** model. The model runs under **your** account, **your** billing, and, where required, **your** contract with the provider. In data protection terms you are the controller of your tenant data, the provider is the processor under your contract, and Bsure only transmits the question and context using the credentials you supply.

***

### Choose your provider

Bsure supports two providers. Pick the one your organization already uses, then follow that guide to create credentials and configure AI Chat.

<table data-view="cards"><thead><tr><th>Provider</th><th>Use when</th><th data-card-target data-type="content-ref">Guide</th></tr></thead><tbody><tr><td><strong>OpenAI</strong></td><td>You have an OpenAI account on the API platform and want the simplest BYOK setup.</td><td><a href="/pages/3ff0fc1d86c907d56de5cbe5b521f85d3e090788">/pages/3ff0fc1d86c907d56de5cbe5b521f85d3e090788</a></td></tr><tr><td><strong>Azure AI Foundry</strong></td><td>You run models in your own Azure subscription, or need Azure data residency</td><td><a href="/pages/56ae7aa25fd26f5c9d4e7a0bd0641195d531d540">/pages/56ae7aa25fd26f5c9d4e7a0bd0641195d531d540</a></td></tr></tbody></table>

***

### Before you start (either provider)

You will need:

* **An administrator in Bsure** with access to **System Settings → System → AI Chat**.
* **A provider account with billing set up.** Usage is pay-as-you-go and billed by the provider to your organization.
* The rights to accept the provider's terms, and to deploy models, on your organization's behalf.

{% hint style="warning" %}
Answers can include personal data about users in your tenant. Treat AI Chat prompts as personal-data processing: document them in your records of processing, execute the provider's data processing agreement, and run a DPIA if your risk assessment calls for one. The provider-specific guides cover how.
{% endhint %}


---

# 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.bsure.io/user-guides/settings/system/ai-chat.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.