← all releases
Anthropic·Mar 9, 2026·Research Preview·paid

Code Review

Code Review is an AI-powered code review system developed by Anthropic, designed to automate and enhance the code review process. It utilizes multiple specialized agents working in parallel to analyze pull requests, aiming to catch bugs and issues that might be missed by human reviewers.

featured on blogAgentic AICodingSoftware Engineering (SW)
visit website
on the blogQodex AI Launches OpenQodex: An Open-Source AI Code Reviewer for Claude Code and Codex 4 min
overview

Code Review is an AI-powered code review system developed by Anthropic, designed to automate and enhance the code review process. It utilizes multiple specialized agents working in parallel to analyze pull requests, aiming to catch bugs and issues that might be missed by human reviewers.

key features
  • 01Automates pull request code review using multiple specialized agents working in parallel.
  • 02Five independent reviewers analyze changes from different angles: CLAUDE.md compliance checking, bug detection, git history context analysis, previous PR comment review, and code comment verification.
  • 03Each finding is scored on a 0-100 confidence scale, and only high-confidence issues (default threshold: 80) are posted as comments, reducing false positives and review noise.
  • 04Intelligently filters out PRs that don't need review—closed, draft, automated, or already-reviewed pull requests are automatically skipped.
  • 05Comments include direct GitHub links with full SHA hashes and line number ranges for easy navigation to the exact code in question.

𝕏 From the Author

related productsbrowse all →
OB-1open sourceOB-1 is a self-improving coding agent developed by OpenBlock Labs, designed to autonomously handle the full development lifecycle, from project management to pull requests. It integrates seamlessly into existing workflows, enhancing productivity and code quality.Mistral Forgeopen sourceMistral Forge is a system designed for enterprises to build frontier-grade AI models grounded in their proprietary knowledge. It enables organizations to train models on internal data, ensuring alignment with unique operations and compliance requirements.CapypaidCapy is an AI software engineer that autonomously triages issues, executes code in isolated virtual machines, and pushes pull requests to GitHub. It enables teams to ship entire sprints in parallel by orchestrating an army of coding agents from a single dashboard.