Anthropic launched Code Review for Claude Code, a multi-agent AI tool that automatically analyzes GitHub pull requests for logical errors, prioritizes findings by severity, and costs $15–$25 per review—addressing the growing bottleneck caused by the surge in AI-generated code in enterprise environments.

Anthropic has released a new multi-agent code review tool for Claude Code, designed to automatically detect bugs and security vulnerabilities in the growing volume of AI-generated code across software development pipelines.