> 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/quality-standards-administration/ai-code-assurance/quality-profiles-for-agentic-ai.md).

# Quality profiles for agentic AI

Managing Sonar agentic AI quality profile in SonarQube Server 2026.5.

## Sonar agentic AI quality profile <a href="#sonar-way-for-agentic-ai-quality-profile" id="sonar-way-for-agentic-ai-quality-profile"></a>

The *Sonar agentic AI* quality profile is a built-in profile that recalibrates Sonar's rules concentrating on six evidence-backed risk categories where agentic AI code actually tends to fail:

* Security boundaries and access control
* Error-handling depth
* Hallucinated APIs and supply-chain risks
* Code duplication and structural drift
* Concurrency correctness
* Performance patterns

The quality profile is recommended for projects where AI agents generate or contribute significant amounts of Java, JavaScript/TypeScript, or Python code. It activates the security and reliability rules most relevant to AI-generated code, while reducing noise from maintainability rules and minor hotspots that are less critical in agentic workflows. Sonar maintains and updates this profile as AI coding patterns and risks evolve.

We recommend you use the *Sonar agentic AI* quality profile in conjunction with the *Sonar way for agentic AI* quality gate if you want to optimize the standards for agent centric development. See [Quality gate for agentic AI](/sonarqube-server/quality-standards-administration/ai-code-assurance/quality-gate-for-agentic-ai.md) for more information.

## Supported languages <a href="#supported-languages" id="supported-languages"></a>

The *Sonar agentic AI* quality profile is currently available for Java, JavaScript/TypeScript, and Python languages.

## Assign quality profile to a project <a href="#assign-quality-profile-to-a-project" id="assign-quality-profile-to-a-project"></a>

To assign the *Sonar agentic AI* quality profile at a project level, navigate to *Your project* > **Project Settings** > **Quality profiles**. Under each supported language, select the *Sonar agentic AI* quality profile.

## Assign quality profile globally <a href="#assign-quality-profile-globally" id="assign-quality-profile-globally"></a>

### Set quality profile as default <a href="#set-quality-profile-as-default" id="set-quality-profile-as-default"></a>

You can set the *Sonar agentic AI* quality profile as the default at the instance level, which means that all projects on the instance will automatically use the profile.

1. Select **Quality Profiles** from the top menu.
2. Filter the quality profiles page by language, see [Supported languages](#supported-languages).
3. From the action menu for the *Sonar agentic AI* quality profile, select **Set as default**.

### Assign quality profile to multiple projects <a href="#assign-quality-profile-to-multiple-projects" id="assign-quality-profile-to-multiple-projects"></a>

If the *Sonar agentic AI* quality profile is not the default one for a given language, you can still assign it to multiple projects.

1. Select **Quality Profiles** from the top menu.
2. Filter the quality profiles page by language, see [Supported languages](#supported-languages).
3. Select the *Sonar agentic AI* quality profile to view its details.
4. In the **Projects** section, select **Change projects**.
5. In the Projects dialog, use the **With**, **Without**, or **All** tabs to select the projects you want to assign the quality profile to.
6. Select **Close**.

## Customizing a quality profile <a href="#customizing-a-quality-profile" id="customizing-a-quality-profile"></a>

Any derivative of the *Sonar agentic AI* quality profile can be extended to cover more rules. See [Creating a quality profile](/sonarqube-server/quality-standards-administration/managing-quality-profiles/creating-a-quality-profile.md) for complete details.

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

* [Managing quality profiles](/sonarqube-server/quality-standards-administration/managing-quality-profiles.md)
* [Quality gate for agentic AI](/sonarqube-server/quality-standards-administration/ai-code-assurance/quality-gate-for-agentic-ai.md)
* [Set your AI standards](/sonarqube-server/quality-standards-administration/ai-code-assurance/overview.md)
* [Monitor projects with AI code](/sonarqube-server/quality-standards-administration/ai-code-assurance/monitor-projects-with-ai-code.md)


---

# 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/quality-standards-administration/ai-code-assurance/quality-profiles-for-agentic-ai.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.