> For the complete documentation index, see [llms.txt](https://docs.sonarsource.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sonarsource.com/sonarqube-server/10.8/user-guide/ai-features.md).

# AI features

SonarQube Server 10.8 can create AI-generated fix suggestions for the issues detected in your projects and guarantee the quality of the AI-generated code.

{% hint style="info" %}
**For AI agents:** You're in the SonarQube Server 10.8 documentation. For a list of all 10.8 pages, see the [SonarQube Server 10.8 page index](https://312504542-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FiJj3TXBdWssTGGg8qK5I%2Fuploads%2FmeJ1nVNGPezOurNrTy4A%2Fsonarqube-server-10.8-llms.txt?alt=media). For the whole site, see the [page index](https://docs.sonarsource.com/llms.txt) or the [full text](https://docs.sonarsource.com/llms-full.txt). For another version, replace 10.8 in the URL with that version. The [latest version](https://docs.sonarsource.com/sonarqube-server/) has no version number in its URL.
{% endhint %}

SonarQube Server can create AI-generated fix suggestions for the issues detected in your projects and guarantee the quality of the AI-generated code.

## AI-generated fix suggestions <a href="#ai-generated-fix-suggestions" id="ai-generated-fix-suggestions"></a>

AI CodeFix is available in SonarQube Server, [Enterprise and Data Center editions](https://www.sonarsource.com/plans-and-pricing/sonarqube/) and uses <code class="expression">space.vars.SQS\_108\_Supported\_LLM\_version</code> to suggest fixes for your issues detected in your projects. To enable the feature, see [Managing AI features](/sonarqube-server/10.8/instance-administration/system-functions/managing-ai-features.md#enabling-ai-generated-fix-suggestions) in the administration section.

To learn how to use this feature, see [Fixing issues](/sonarqube-server/10.8/user-guide/issues/fixing.md#getting-ai-generated-fix-suggestions) on the *Fixing issues* page.

## AI Code Assurance <a href="#ai-code-assurance" id="ai-code-assurance"></a>

AI Code Assurance features help you make sure that the AI-generated code in your project is clean. A new recommended quality gate, *Sonar way for AI Code*, is available to use on projects. In addition, it’s possible to qualify any quality gate for [AI standards](/sonarqube-server/10.8/instance-administration/analysis-functions/ai-standards.md) and start using it on your projects. and start using it on your projects to ensure security and code quality while boosting team productivity with AI tools.

To learn more about protecting AI-generated code in your project, see the [AI standards](/sonarqube-server/10.8/instance-administration/analysis-functions/ai-standards.md#enabling-ai-code-assurance) article on the *Standards for AI-generated code* page.


---

# 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.sonarsource.com/sonarqube-server/10.8/user-guide/ai-features.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.
