> 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-cloud/managing-your-projects/issues/with-ai-features.md).

# With AI features

Use SonarQube Cloud's AI features, including Remediation Agent, AI CodeFix, and Hunter Agent, to find and fix issues in your code.

SonarQube Cloud offers AI features for working through your issues: SonarQube Remediation Agent, which proposes fixes as pull requests; AI CodeFix, which generates a fix for a single issue on demand; and SonarQube Hunter Agent, which raises complex, logic-level vulnerabilities as issues you triage. These are part of Sonar's [Agent Centric Development Cycle](https://docs.sonarsource.com/agent-centric-development-cycle/).

## Remediation Agent

SonarQube Remediation Agent runs an independent review and analysis, then proposes fixes in a new pull request for you to review. It works on issues found in your pull requests and on the backlog of issues in your main branch. It also proposes fixes for Hunter Agent findings. To learn how the agent works, see [Remediation Agent](https://docs.sonarsource.com/agent-centric-development-cycle/in-your-long-living-branches-the-code-maintenance-loop/remediation-agent.md). To enable it for your organization, see [Administer Remediation Agent](https://docs.sonarsource.com/sonarqube-cloud/administering-sonarcloud/ai-features/administer-remediation-agent.md).

Remediation Agent requires a separate subscription to your SonarQube Cloud Team (annual) or Enterprise plan.

{% content-ref url="/pages/9vNPOGvpaHaMOcNJANde" %}
[Pull request fix suggestions](https://docs.sonarsource.com/sonarqube-cloud/managing-your-projects/issues/with-ai-features/pull-request-fix-suggestions.md)
{% endcontent-ref %}

{% content-ref url="/pages/BkwLX6gm79ZCI7Reb5F1" %}
[Backlog fix suggestions](https://docs.sonarsource.com/sonarqube-cloud/managing-your-projects/issues/with-ai-features/backlog-fix-suggestions.md)
{% endcontent-ref %}

{% content-ref url="/pages/8qjgq7yDwdyhzfPtY6Jj" %}
[Remediation campaigns](https://docs.sonarsource.com/sonarqube-cloud/managing-your-projects/issues/with-ai-features/remediation-campaigns.md)
{% endcontent-ref %}

{% content-ref url="/pages/UAwoECZ6Szdjhetjdv9w" %}
[Remediation Agent learning](https://docs.sonarsource.com/sonarqube-cloud/managing-your-projects/issues/with-ai-features/remediation-agent-learning.md)
{% endcontent-ref %}

### Agent activity <a href="#agent-activity" id="agent-activity"></a>

Every run of SonarQube Remediation Agent is recorded in one place, whichever flow triggered it. To review the agent's activity, go to *Your SonarQube Cloud Project* > **Agent activity**. From there you'll see the agent's:

* Status/duration: Time the agent spent to generate fixes.
* Started: When the run was triggered. Runs start on a schedule, from **Fix with Agent** or **Start a campaign** on the **Issues** page, from **Fix automatically** on GitHub, or from **Fix with Agent** in SonarQube Cloud for a GitLab merge request.
* Source: Where the agent is working. *Backlog fixes* identifies manual and scheduled backlog runs. **Campaign** identifies a Remediation campaign. Pull request runs link to the branch where you called the agent.
* Outcome: A link to the agent's pull request or GitLab merge request.
  * Pull requests and merge requests made for *Backlog fixes* target your main branch. See [Backlog fix suggestions](https://docs.sonarsource.com/sonarqube-cloud/managing-your-projects/issues/with-ai-features/backlog-fix-suggestions.md) for details.
  * Pull requests and merge requests made for *Pull request fixes* target your original branch. See [Pull request fix suggestions](https://docs.sonarsource.com/sonarqube-cloud/managing-your-projects/issues/with-ai-features/pull-request-fix-suggestions.md) for details.
  * Remediation campaigns combine changes on a campaign branch. Expand the campaign to see its steps and their PRs, then review the final PR into your main branch. See [Remediation campaigns](https://docs.sonarsource.com/sonarqube-cloud/managing-your-projects/issues/with-ai-features/remediation-campaigns.md) for instructions.

If reviewers comment on the agent's GitHub PR, the agent can follow up on their feedback. Check the PR description and review threads for progress. See [Review comment follow-up](https://docs.sonarsource.com/sonarqube-cloud/managing-your-projects/issues/with-ai-features/pull-request-fix-suggestions.md#review-comment-follow-up).

![The SonarQube Cloud Agent activity page lists each of the agent's event moments on your pull request analyses.](https://docs.sonarsource.com/~gitbook/image?url=https%3A%2F%2F2223713658-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FB4UT2GNiZKjtxFtcFAL7%252Fuploads%252Fzo0hYjsJKgxztCAKN7rG%252Fsonarqube-cloud-agent-activity.png%3Falt%3Dmedia%26token%3D84d47193-c5c7-486e-98d9-0c59d420da1d\&width=768\&dpr=3\&quality=100\&sign=98c996d1\&sv=2)

## AI CodeFix

AI CodeFix generates a fix suggestion for an individual issue, which you review in SonarQube Cloud or open in your IDE. See [Getting AI-generated fix suggestions](https://docs.sonarsource.com/sonarqube-cloud/managing-your-projects/issues/fixing.md#getting-ai-generated-fix-suggestions) to use it, and [AI CodeFix](https://docs.sonarsource.com/agent-centric-development-cycle/in-your-long-living-branches-the-code-maintenance-loop/ai-codefix.md) to learn how it works.

## Hunter Agent

SonarQube Hunter Agent runs a deep AI-powered analysis to find vulnerabilities that require human-like understanding of the code, such as broken access control and business-logic flaws, then raises them as issues you triage like any other. To learn how the agent works, see [Hunter Agent](https://docs.sonarsource.com/agent-centric-development-cycle/in-your-long-living-branches-the-code-maintenance-loop/hunter-agent.md). To enable it for your organization, see [Hunter Agent (administration)](https://docs.sonarsource.com/sonarqube-cloud/administering-sonarcloud/ai-features/hunter-agent.md).

Hunter Agent requires a separate subscription to your SonarQube Cloud annual Team or Enterprise plan.

{% content-ref url="/pages/ERCfr5hb5fcaktH0xT8n" %}
[Hunter Agent findings](https://docs.sonarsource.com/sonarqube-cloud/managing-your-projects/issues/with-ai-features/hunter-agent-findings.md)
{% endcontent-ref %}


---

# 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-cloud/managing-your-projects/issues/with-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.
