# AI Code Review

> **Alpha:** AI Code Review is currently in alpha.

## Overview

AI Code Review is part of the *Verify* phase of the [Agent Centric Development Cycle](/agent-centric-development-cycle/readme.md).

AI Code Review combines SonarQube's deterministic static analysis with context-aware AI. Engineers can review, understand, and approve code faster. It posts inline review comments, change summaries, and on-demand walkthroughs and architecture diagrams directly on pull requests.

<figure><img src="/files/1iw0WZ9YVtMWq9jcae4l" alt="Sonar Review summary with options to generate walkthrough and diagram"><figcaption></figcaption></figure>

## Supported languages

AI Code Review delivers the best results for languages supported by SonarQube static analysis—findings are correlated with and validated against deterministic scan results. It can also review code in unsupported languages, but those reviews rely on AI analysis alone and may be less complete.

For the full list of languages supported by SonarQube Cloud analysis, refer to the [SonarQube Cloud language support](/sonarqube-cloud/discovering-sonarcloud/overview.md) documentation.

## Setup

See [Get AI reviews in pull requests](/agent-centric-development-cycle/how-to-guides/verify-your-code/get-ai-reviews-in-pull-requests.md) to learn how to set up code reviews in your pull requests.

## Related pages

* [Get AI reviews in pull requests](/agent-centric-development-cycle/how-to-guides/verify-your-code/get-ai-reviews-in-pull-requests.md)
* [Guide-and-Verify loop](/agent-centric-development-cycle/features/agentic-analysis.md#guide-and-verify-loop)
* [About the Agent Centric Development Cycle](/agent-centric-development-cycle/readme.md)


---

# Agent Instructions: 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:

```
GET https://docs.sonarsource.com/agent-centric-development-cycle/features/ai-code-review.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.