> 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/chat.md).

# Chat

Ask a question about your tenant in plain language, and get an answer with the data behind it, not a report you have to go build yourself.

It is designed to answer simple but important questions:

* Do we have administrator users without MFA?
* How many global admins do we have?
* Are leavers actually disabled?
* Which app secrets or certificates expire soon?
* Give me a board-ready security posture summary.
* Do we have stale guest accounts?

You don't need to be an Entra ID administrator, or know which Bsure report to open, to get an answer. Ask about your tenant, licensing, or security posture, and Chat turns the question into the right lookup.

Chat works best on a specific, named question. "Which users don't have MFA?" gets you a table. "What's actually in my tenant right now?" or "What changed since I last looked?" is too broad today. Chat will ask you to narrow it rather than guess.

***

## What you get back

Every answer includes:

* A direct answer to your question, in plain language.
* A table pulled straight from your data. That table, not the text around it, is the source of truth. Treat the surrounding text as the AI's interpretation, and use the table to check it.
* What was actually measured, and as of when.
* A recommended next step.

You can expand the answer to see the plan behind it and how it ran, if you want to check the reasoning before acting on it.

## A word on trust

Answers are written by AI from your tenant's data, and can be incomplete or wrong. Spot-check the table before you act on a finding, the same way you'd sanity-check a number from any report.

Chat sessions aren't stored. They survive a tab refresh but are lost on server restart, aren't visible on other devices, and don't serve as an audit trail. If you need a record of a decision, that lives on [Assessments](/user-guides/assessments.md), via [Accepting risk](/user-guides/assessments.md#accepting-risk), not in a chat session.

## Who it's for

Built for the person who owns the risk or compliance answer, not necessarily the person who administers Entra ID or lives inside Bsure's reports day to day. A CISO can get a straight answer without asking IT to pull a report first.

***

## Turning it on

Chat is a beta feature, off by default and you need to contact [Support](/support/support.md) to enable it for your tenant . An administrator enables it and connects a provider (OpenAI or Azure AI Foundry) under bring-your-own-key billing.

See [AI Chat setup](/user-guides/settings/system/ai-chat.md) for how to turn it on and configure a provider.


---

# 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.bsure.io/user-guides/chat.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.
