> 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
You can fix the issues SonarQube Cloud finds with two AI features: the SonarQube Remediation Agent, which proposes fixes as pull requests, and AI CodeFix, which generates a fix for a single issue on demand. Both are part of Sonar's [Agent Centric Development Cycle](https://docs.sonarsource.com/agent-centric-development-cycle/).
## Remediation Agent
The 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. To learn how the agent works, see [Remediation Agent](/agent-centric-development-cycle/in-your-long-living-branches-the-code-maintenance-loop/remediation-agent.md). To enable it for your organization, see [Administer the Remediation Agent](/sonarqube-cloud/administering-sonarcloud/ai-features/administer-remediation-agent.md).
The Remediation Agent is part of Sonar Agent Essentials, a product that requires a separate subscription to your SonarQube Cloud Team (annual) or Enterprise plan.
{% content-ref url="/pages/9vNPOGvpaHaMOcNJANde" %}
[Pull request fix suggestions](/sonarqube-cloud/managing-your-projects/issues/with-ai-features/pull-request-fix-suggestions.md)
{% endcontent-ref %}
{% content-ref url="/pages/BkwLX6gm79ZCI7Reb5F1" %}
[Backlog fix suggestions](/sonarqube-cloud/managing-your-projects/issues/with-ai-features/backlog-fix-suggestions.md)
{% endcontent-ref %}
### Agent activity
Every run of the 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 agent is triggered by the **Automated backlog remediation** schedule, by selecting **Assign to Agent** on the **Issues** page, or by selecting **Fix automatically** in the **Quality Gate failed** comment on a pull request.
* Source: Where the agent is working. *Backlog fixes* means that the agent is working on issues found in your main branch; or a link will be provided to the branch where you first called the agent.
* Outcome: A link to the agent's PR.
* PRs made for *Backlog fixes* will be on your `main` branch. See [Backlog fix suggestions](/sonarqube-cloud/managing-your-projects/issues/with-ai-features/backlog-fix-suggestions.md) for details.
* PRs made for *Pull request fixes* will be made on your branch. See [Engage with the agent](/sonarqube-cloud/managing-your-projects/issues/with-ai-features/pull-request-fix-suggestions.md#engage-with-the-agent) for details.
## 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](/sonarqube-cloud/managing-your-projects/issues/fixing.md#getting-ai-generated-fix-suggestions) to use it, and [AI CodeFix](/agent-centric-development-cycle/in-your-long-living-branches-the-code-maintenance-loop/ai-codefix.md) to learn how it works.
---
# 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-cloud/managing-your-projects/issues/with-ai-features.md?ask=&goal=
```
`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.