Code Review at Anthropic: How the Claude Code Team Reviews AI-Generated Code

ArticleAddy Osmani, Morgan Westlee Lunt, Qing WangResource

The Claude Code engineering team explains how they handle code reviews when agents write around 90 percent of the codebase. Instead of exhaustive manual line-by-line checks, they rely on pre-PR verification, automated multi-agent reviews, risk-tiered human approvals, and rapid rollbacks.

Key points

  1. Anthropic's monorepo went from 2,500 landed changes per day in May to over 30,000 in September, while Claude Code merged PRs doubled and revert rates dropped over 40 percent.
  2. Verification begins locally: Claude runs tests or builds, and subagents review diffs against project rules in CLAUDE.md and REVIEW.md before PR creation.
  3. Pull requests undergo an automated review where multiple agents hunt for bugs and vote on findings, filtering out noise and blocking merges until resolved.
  4. Automated security scans and CI pipelines must be green, with findings cleared either by code fixes or justified dismissals.
  5. Human approvals scale by risk tier determined by classifiers: low-risk changes by trusted authors require no human approval, medium risk needs one person, and high risk requires two.
  6. Past incidents and reverts are converted into an automated evaluation suite run daily to iteratively improve the reviewer agents.

Why it matters

As coding agents drastically accelerate code generation, traditional peer review processes cannot keep pace. Anthropic demonstrates an operational framework for conserving human attention for genuinely high-risk architectural concerns without compromising repository health.

Analysis

Anthropic illustrates a transition from end-of-line human gating to continuous automated assurance. By embedding guardrails into instructional files like CLAUDE.md and automating consensus-based bug detection, the team treats human review as a scarce resource. Measuring revert rates and tracking incident benchmarks ensures that lowering manual review time does not simply transfer work to post-release troubleshooting.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 19 October 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • X post:ClaudeDevs

    How the Claude Code Team Redesigned Code Review for AI

    Around 90 percent of Claude Code is written by Claude itself. The Anthropic engineering team shares how shifting to automated, multi-layered reviews more than doubled merged pull requests while cutting reverts by over 40 percent.

    10kbookmarks1.6mviews

    AI & LLMs· Opinion

  • Article:Anthropic

    Claude Code Power User Tips from Anthropic's Engineering Team

    Engineers from the Claude Code team at Anthropic share core workflow patterns for shipping code faster, highlighting parallel execution via Git worktrees, plan-first workflows, automated verification, and persistent project memory.

    AI & LLMs· Resource

  • X post:Casey Lee

    Anthropic's AI-Native SDLC Playbook: Scaling Pipelines for Fast Coding Agents

    Casey Lee highlights Anthropic's AI-native SDLC playbook. While agents like Claude Code can generate PRs within hours, traditional security reviews and product sign-offs still take days. Anthropic proposes structuring planning, reviews, and releases into agent-executable steps governed by human checkpoints.

    276bookmarks22kviews

    AI & LLMs· Opinion

  • Video

    Video:CURT

    How Anthropic Builds Software: Thariq Shihipar on Claude Code and the Future of Engineering

    In an interview with Ryan Peterman, Thariq Shihipar, an engineer on Anthropic's Claude Code team, discusses how engineering practices are evolving alongside advanced AI models. At Anthropic, developers treat Claude as a thought partner operating at higher levels of abstraction, with manual IDE coding largely diminishing. Shihipar discusses the critical role of harness engineering, loop engineering workflows, verification strategies to prevent incidents, and why foundational technical knowledge remains vital even as coding becomes increasingly automated.

    AI & LLMs· Talk

  • Link:Anthropic

    Anthropic examines progress towards recursive self-improvement in AI

    The Anthropic Institute shares internal metrics and external benchmark trends demonstrating how AI agents are accelerating the development of subsequent AI models. As of May 2026, over 80% of merged code at Anthropic is written by Claude, with engineers merging 8x more code per day than in 2024. While full recursive self-improvement remains constrained by models' lack of strategic judgement in goal selection, progress is advancing rapidly.

    AI & LLMs· Research

  • Article:Ryan Peterman

    How Anthropic Builds and How Engineering Will Change Soon

    In this episode of The Peterman Pod, host Ryan Peterman interviews Thariq Shihipar from Anthropic's Claude Code team about how Anthropic uses models for internal engineering and how software engineering will evolve.

    AI & LLMs· Discussion

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.