Anthropic launches a new code review tool to check AI-generated content - but it might cost you more than you'd hope

• Code Review is a multi-agent Claude Code tool to iron out any AI-generated code issues
• Token-based pricing typically results in a $15-25 charge, Anthropic says
• 84% of large pull requests got issues flagged, averaging 7.5 findings

In response to ongoing studies questioning the accuracy of AI coding tools, particularly the security and privacy credentials of their output, Anthropic has launched a new tool to review code in GitHub pull requests.

Code Review for Claude Code uses multiple agents to maximize accuracy, searching for "logic errors, security vulnerabilities, broken edge cases, and subtle regressions" (via support documentation).

The tool will then highlight any findings as inline comments, with a summary comment, on the pull request to help developers identify any issues more clearly.

Code Review is Claude's answer to insecure AI-generated code

Anthropic also noted the agents verify findings and rank issues by severity in order to reduce false positives, while also cross-referencing with the entire codebase as context, not just the diff.

Pricing for the new tool is token-based, but Anthropic said on average a typical pull request will cost around $15-25 depending on size and complexity. A review will usually take around 20 minutes, but again, this is just a guide.

The timing of this new feature launch isn't insignificant either – Anthropic says code output per engineer has grown 200% in the past year with a marked rise in vibe coding, and there's now a clear bottleneck in the reviewing process.

Anthropic also claims to use Code Review for Claude Code on nearly every pull request internally, and it's seen great success from the tool. Early data shows that 84% of large pull requests (1,000+ lines) contain findings, averaging 7.5 issues, while small pull requests (under 50 lines) still average 0.5 issues, with 31% of them receiving comments.

Emphasizing the tool's accuracy, the company also added that fewer than 1% of issues flagged go on to be rejected by human developers.

Code Review is currently available as a research preview for Claude Teams and Enterprise plans – Anthropic didn't share details of a wider rollout, but we expect that to come with time.

Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds. Make sure to click the Follow button!

And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form, and get regular updates from us on WhatsApp too.