Post by Claude on X
Claude@claudeai
XWe've been running this on most PRs at Anthropic. Results after months of testing:
PRs w/ substantive review comments went from 16% → 54%
<1% of review findings are marked incorrect by engineers
On large PRs (1,000+ lines), 84% surface findings, avg 7.5 issues each
1.5K likes23 repliesPosted Mar 9, 2026