Anthropic introduces code review feature for Claude code

Anthropic has introduced a new feature called Code Review for its Claude coding assistant, which is currently rolling out in beta exclusively for Team and Enterprise plans. This feature utilizes parallel AI agents to identify bugs across complete codebases, significantly reducing the occurrence of false positives. Notably, Anthropic has already been employing Code Review for nearly all internal pull requests, aiming to enhance the development process for its developers.

Claude: Claude is Anthropic’s family of state-of-the-art large language models optimized for coding, agentic tasks, and professional workflows, with recent models like Sonnet 4.6 showing advanced capabilities in large codebase management and code review. It serves as the core intelligence behind tools like Claude Code. The new Code Review feature leverages Claude to deploy AI agents for bug detection in software projects.
Anthropic: Anthropic is an AI safety and research company developing the Claude family of large language models aimed at creating reliable, interpretable, and steerable AI systems. It provides specialized tools such as Claude Code, an AI coding assistant that handles codebase analysis and editing. Anthropic announced the introduction of Code Review, a new feature for Claude Code that automates comprehensive pull request reviews.
Code Review: Code Review is a beta feature integrated into Claude Code designed to dispatch parallel AI agents that analyze entire code projects for logic bugs and issues, extending beyond just modified files. It produces inline comments and summary reports to streamline developer reviews of pull requests. Anthropic utilizes Code Review internally on nearly all its pull requests to enhance development efficiency.

Adoption: Anthropic employs Code Review on almost all internal pull requests to assist developers.
Availability: Code Review is rolling out in beta exclusively for Team and Enterprise plans.
Capabilities: The feature uses parallel AI agents to identify bugs across full codebases with fewer false positives.

Source: DegenerateNews

Source