Anthropic Details AI-Driven Code Review Process for Claude Code

Anthropic has outlined how the Claude Code team manages code reviews as AI agents increasingly contribute to its codebase. This approach relies on multiple layers of automated verification, AI-powered reviews, and risk-based human approval, aiming to reduce manual review time without increasing regressions or production incidents.
Addy Osmani, Morgan Westlee Lunt, and Qing Wang explained that the team’s review process has evolved alongside the growing volume of AI-generated code. Between June and September, merged pull requests to the Claude Code repository more than doubled, while the proportion of changes requiring a revert fell by over 40%.
Rather than relying on traditional line-by-line reviews, the team has moved much of the verification earlier in the development process. Before opening a pull request, Claude runs tests, builds, and linters, while a separate agent reviews the changes in a fresh context.
Every pull request then undergoes several automated checks. Claude-powered reviewers inspect code changes for potential bugs, with multiple agents independently investigating findings before another group verifies them. A separate security review can also block a merge if unresolved issues remain.
This method raises questions about the evolving boundaries between software engineering, testing, and quality assurance. As one commenter noted, this shift prompts discussions about whether code review is synonymous with testing and the role of QA teams.
Human involvement depends on the risk associated with a change. Low-risk modifications, such as documentation updates or internal features behind feature flags, may require no human approval. Medium-risk changes require one person, while high-risk modifications need two approvals. Changes to particularly sensitive areas, including CI workflows, always require human oversight.
The team has also introduced mechanisms to prevent automated reviews from generating excessive feedback. Review cycles are capped at three rounds before the author is asked to reconsider the implementation. Subsequent reviews focus on new changes rather than repeatedly examining the entire pull request.
These adjustments have improved review efficiency. According to Anthropic, the share of internal pull requests passing after one review and fix round increased from 65% to 78%. Meanwhile, the proportion requiring five or more rounds dropped from 8.9% to 1.5%.
Human reviewers remain responsible for architectural decisions, product direction, high-risk changes, and the final outcome. The team emphasizes that the person directing an AI agent is accountable for the code it produces.
Anthropic’s approach extends beyond code review itself. Merged changes are typically released behind feature flags, tested internally, and gradually rolled out to users. Incidents and reverted changes are also incorporated into the review process.
Source: InfoQ