Anthropic launches code review tool to check flood of AI-generated code

Anthropic has launched Code Review inside Claude Code, a multi-agent tool that automatically analyzes pull requests for logic errors, explains issues step by step, and labels severity with color codes. Targeting enterprise customers like Uber, Salesforce, and Accenture, it integrates with GitHub and runs in parallel agents to handle the surge in AI-generated code. Each review costs an estimated $15–$25 on average. The launch coincides with Claude Code's run-rate revenue surpassing $2.5 billion and enterprise subscriptions quadrupling since the start of the year.