> 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/2026.2/instance-administration/ai-features/overview.md).

# Overview

SonarQube Server offers several instance-level AI features designed to enhance code quality and security.

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

Sonar’s AI CodeFix employs large language models to propose automatic code fixes. Instance administrators have the option to activate this feature and select one of the available LLMs. Once enabled, developers can view AI-generated fix suggestions for compatible languages through the SonarQube Server interface or directly in their IDEs when in connected mode. The goal of AI CodeFix is to simplify issue resolution and enhance code quality by leveraging AI-powered assistance.

See the [Enable AI CodeFix](/sonarqube-server/2026.2/instance-administration/ai-features/enable-ai-codefix.md) page.

## Autodetect AI-generated code <a href="#autodetect-ai-code" id="autodetect-ai-code"></a>

{% hint style="warning" %}
**Deprecated:** Autodetect AI Code is still available in SonarQube Server 2026.1 LTA and will be removed in a future release. See the [deprecation policy](/sonarqube-server/2026.2/server-update-and-maintenance/maintenance/deprecations/deprecation-policy.md) for more information. Manual labeling of projects containing AI code remains available — see [Label projects with AI code](/sonarqube-server/2026.2/quality-standards-administration/ai-code-assurance/overview.md#label-projects-with-ai-code).
{% endhint %}

SonarQube Server includes a feature that automatically identifies AI-generated code from your DevOps platform. This functionality, active by default, notifies instance administrators about projects with recent AI activity, allowing for the implementation of Sonar’s AI Code Assurance. To enable this, SonarQube Server needs specific permissions to access information on your DevOps platform to compare AI usage statistics.

See the [Autodetect AI code](/sonarqube-server/2026.2/instance-administration/ai-features/autodetect-ai-code.md) page.

## Permissions for AI autodetection <a href="#permissions-for-ai-autodetect" id="permissions-for-ai-autodetect"></a>

{% hint style="warning" %}
**Deprecated:** Autodetect AI Code is still available in SonarQube Server 2026.1 LTA and will be removed in a future release. See the [deprecation policy](/sonarqube-server/2026.2/server-update-and-maintenance/maintenance/deprecations/deprecation-policy.md) for more information. Manual labeling of projects containing AI code remains available — see [Label projects with AI code](/sonarqube-server/2026.2/quality-standards-administration/ai-code-assurance/overview.md#label-projects-with-ai-code).
{% endhint %}

To detect AI-generated code, SonarQube Server needs access to the DevOps AI provider. The AI Code Autodetection feature must be enabled by an instance administrator in SonarQube Server, and the DevOps administrator must grant the necessary permissions on the DevOps platform. This setup allows SonarQube Server to analyze AI-assisted usage and identify potential AI contributions, showing the detection status on project overview pages.

See the [Permissions for AI autodetect](/sonarqube-server/2026.2/instance-administration/ai-features/permissions-for-ai-autodetect.md) page.

## Related pages <a href="#related-pages" id="related-pages"></a>

* [Agent Centric Development Cycle](https://docs.sonarsource.com/agent-centric-development-cycle/) of AI capabilites
* Learn how to[Set your AI standards](/sonarqube-server/2026.2/quality-standards-administration/ai-code-assurance/overview.md) for AI Code Assurance
* [Fixing issues](/sonarqube-server/2026.2/user-guide/issues/fixing.md#opening-in-ide) for information about getting AI CodeFix in the IDE


---

# 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.sonarsource.com/sonarqube-server/2026.2/instance-administration/ai-features/overview.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.