The AI Record
We've been running Code Review internally for months: on large PRs (over 1,000 lines changed), 84% get findings, averaging 7.5 issues. On small PRs under 50 lines, that drops to 31%, averaging 0.5 issues. Engineers largely agree with what it surfaces: less than 1% of findings are marked incorrect.

AnthropicPublished by the organization itself (post), no named author

Post: Bringing Code Review to Claude Code, claude.com (Anthropic), March 9, 2026, at Code Review in action.

  • 1% findings marked incorrect, internal use for months before March 2026 (upper bound, 'less than 1%'). A person approves

Checked against the source [ Grade B ] Said in the last year Anthropic: $47 billion revenue, run-rate, May 2026 Sells AI tools

Filed under

Anthropic sells AI or agent tools or services, so it has a reason to publish flattering numbers about AI. The passage stays in the archive; read it with that in mind.

How this was checked

Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Claude Sonnet), blind second pass from passage text and citation only, no repository access, 2026-11-07).

Exact match for all four sentences, including 84%, 7.5, 31%, 0.5 and 'less than 1%'. It is Anthropic's own post.

How to cite this passage

Anthropic, “Bringing Code Review to Claude Code”, claude.com (Anthropic), 2026-03-09, at Code Review in action. https://claude.com/resources/articles/code-review Archived at https://the-ai-record.com/passages/anthropic-large-prs-84-get-findings-under-1-percent-incorrect-2026

More from the same source

Code output per Anthropic engineer has grown 200% in the last year. Code review has become a bottleneck, and we hear the same from customers every week.

AnthropicPublished by the organization itself (post), no named author

Post: Bringing Code Review to Claude Code, claude.com (Anthropic), March 9, 2026, at Managing the review bottleneck.

  • 200% code output per engineer, the last year before March 2026. Level not stated

Checked against the source [ Grade B ] Said in the last year Anthropic: $47 billion revenue, run-rate, May 2026 Sells AI tools Passage page

We run Code Review on nearly every PR at Anthropic. Before, 16% of PRs got substantive review comments. Now 54% do. It won't approve PRs — that's still a human call — but it closes the gap so reviewers can actually cover what's shipping.

AnthropicPublished by the organization itself (post), no named author

Post: Bringing Code Review to Claude Code, claude.com (Anthropic), March 9, 2026, at Managing the review bottleneck.

  • 54% prs with substantive review comments, after Code Review, before March 2026 (up from 16%). A person approves

Checked against the source [ Grade B ] Said in the last year Anthropic: $47 billion revenue, run-rate, May 2026 Sells AI tools Passage page

Something wrong? Report a correction. JSON: /api/v1/passages/anthropic-large-prs-84-get-findings-under-1-percent-incorrect-2026.json