- Anthropic unveiled a multi-agent Code Review system for Claude Code that automatically reviews every PR for bugs.
- It dispatches parallel AI agents to review pull requests and adds inline comments where the issue is found.
- On an average, the review takes 20 minutes to complete. It's available to Team and Enterprise customers only.
Anthropic just launched a new Code Review feature in its popular Claude Code AI tool. It’s a multi-agent review system that dispatches a team of agents to catch bugs after every pull request. Code Review is modeled on the system that Anthropic uses internally for nearly every PR. It’s also a better alternative than the open-source Claude Code GitHub Action tool.
Code Review is Anthropic’s Answer to the Pull Request Flood
The Code Review system in Claude Code is currently in research preview and available for Team and Enterprise customers only. As for how the feature works, when a PR opens or updates, multiple AI agents analyze the diff from different angles. Five independent reviewers check the changes such as CLAUDE.md compliance, bug detection, git history context, previous PR comment review, and code comment verification.
Now, the issues are ranked by severity and posted as inline comments on the specific lines. And to reduce false positives, only high-confidence issues (above 80 threshold) are posted. The average review takes about 20 minutes to complete.
Note that Code Review will not approve PRs, so human reviewers can still make that decision. Next, it focuses on code correctness and looks for bugs that might break production, instead of looking for formatting preferences or missing test coverage. Of course, you can modify the CLAUDE.md file and tune what kind of issues Claude can flag.
To enable it, team admins can open Claude Code admin settings, and install the Claude GitHub app. Now, simply select the repository and you are done. Individual developers don’t need to do anything. Once enabled, it runs automatically on new PRs.
