Anthropic Introduces Agentic Code Review Tool to Claude Code

Anthropic introduced a new artificial intelligence (AI)-powered coding tool on Monday, aimed at reviewing pull requests (PRs) before they are deployed. Dubbed Code Review, it is available as a new tool in Claude Code, and it can be activated for specific or all repositories. The company said the tool uses a multi-agent review system and is designed to be thorough. The AI firm also claimed that the new agentic tool is similar to one it runs internally for “nearly every PR.”

Code Review Comes to Claude Code

In a post, the San Francisco-based AI startup announced and detailed the new AI tool. With the rise of vibe coding platforms and AI assistants that can write and edit code, organisations are now seeing a high volume of code submissions. Anthropic says this increased volume often results in overworked human reviewers skimming through the code instead of analysing it in detail.

This can lead to code with bugs and severe flaws getting approved and being deployed in critical codebases. Anthropic's solution to the problem is Code Review, which is said to be capable of conducting “deep, multi-agent reviews that catch bugs human reviewers often miss themselves.”

Activating Code Review for an organisation requires admin approval. Admins need to enable the tool in the Claude Code settings, install the GitHub App, and select the repositories where the AI will review the PRs. Once done, reviews run automatically on all new PRs without any additional configuration.

After the tool receives a PR, Code Review sends a team of AI agents that search for bugs in parallel, verify them to eliminate false positives, and rank them by severity. Large or complex PRs get more agents and a deeper read, whereas trivial code gets a lighter treatment. An average review can take up to 20 minutes. Once the analysis is done, the result is added to the PR as a single overview comment (alongside in-line comments for specific bugs).

Anthropic claims Code Review is more thorough and expensive compared to the open-source Claude Code GitHub Action. The tool is billed on token usage, and the company says an average bill can be between $15 (roughly Rs. 1,380) and $25 (roughly Rs. 2,300). Organisations can control their spend by defining total monthly spends across reviews, by enabling the tool on select repositories, and by tracking its performance via the analytics dashboard.