Opening article
How the Claude Code team does code review
Claude Code’s team reviews the majority of its 90% agent‑written code through automated checks before any human review. The process evolved from a gate‑at‑the‑end model to continuous, spell‑check‑style reviews that catch routine mistakes, reserving human attention for higher‑level issues. The system tracks human approvals, comments, and wait times to ensure that most pull requests merge with at most one human in the loop without increasing reverts or incidents.
Benchmark Metric
90%
Reported Accuracy / GainAccess Mode
API & Platform
Managed Enterprise CloudCategory
Models
Industry DomainThe Core Development
We've said before that Claude writes about 90 percent of Claude Code's own code. So how do we review code at the volume we produce it? Does anyone read code anymore? And if something breaks, who catches it?
This post covers the code review flow on the Claude Code team and how it has evolved. From June to September, merged pull requests to Claude Code's codebase more than doubled while the share that had to be reverted fell by more than 40 percent.
We didn't remove review. But we did move most of the reading to machines, optimized for human time and attention, and invested heavily in making it fast and easy to undo mistakes.
Real-World Use Cases & Applications
So the goal is that most pull requests in the Claude Code repos (the CLI, the desktop and web apps, and the mobile apps) merge with at most one human in the loop, who can be the author, with no increase in reverts or incidents. To measure human time, we track human approvals per PR (median and 95th percentile), human comments, and how long a PR waits on a person. Revert and incident rates are the guardrail: if they rise, we haven't saved human time, we've only moved it.
The change sets the tier, not the author. A classifier reads the change and picks its risk tier. A second classifier asks whether this particular change needs another person even when its tier says it doesn't. Some paths always need a person, anything owners have listed as sensitive and any CI workflow file.
Strategic Perspective & Ecosystem Impact
When agents write code, the number of changes goes up, fast. In Anthropic's monorepo, changes landing per day went from about 2,500 in May to more than 30,000 in September this year.
Claude Code lives in its own repository, separate from the monorepo, but it's seeing a lot of pressure too. When you are shipping this fast, manual, line-by-line code review is incredibly difficult if not impossible.
This article mainly focuses on finding and fixing issues, but we will come back to the second job near the end.
Why it matters
By automating the bulk of code review, Claude Code demonstrates how AI can scale software production while preserving human oversight, a model that could reshape development workflows across the AI industry.
Topic dossiers Anthropic & Claude