12 weeks
“CodeRabbit saved approximately 12 weeks of human reviewer effort.”
As published on coderabbit.ai. Captured by usedby on Oct 8, 2026.
What happened
EarnIn uses CodeRabbit as an automated first-pass reviewer on pull requests across hundreds of GitHub repositories. It is combined with central configuration, repository-level guidance, and AST-grep rules so human reviewers can focus on architecture and risk in a regulated financial services environment.
Summary written by usedby from the source page, in English. The figures are those of CodeRabbit and EarnIn, not ours.
- 60%“CodeRabbit reviewed that stream with more than 8,000 comments and an overall acceptance rate of approximately 60%.”
- 5,000“Over a recent 90-day period, EarnIn merged more than 5,000 pull requests across hundreds of active repositories.”
- 1,000“In the first few weeks of the proof of concept, CodeRabbit reviewed more than 1,000 pull requests, and EarnIn engineers were already accepting a meaningful share of its suggestions.”
- 1.5 comments“CodeRabbit averaged roughly 1.5 comments per pull request, compared with roughly 2.0 comments from human reviewers.”
Across the same period, CodeRabbit saved approximately 12 weeks of human reviewer effort. For a distributed engineering organization operating hundreds of repositories, that recovered capacity creates more room for design discussions, platform work, and production readiness.
CodeRabbit scales reviews across hundreds of engineers and repos in a way manual review processes simply cannot. The measurable outcomes are real: solid acceptance ratios, quantified time savings, and consistent first-pass coverage for every PR.
What the story claims, and what we checked
We compared the story with its live page on Oct 8, 2026.
- The figure: 12 weeksCheckedPrinted word for word on the page, near the name of EarnIn.
- The passage quoted aboveCheckedCopied word for word from the page, near the name of EarnIn.
- EarnIn uses CodeRabbitCheckedConfirmed line. Latest check across sources: Oct 8, 2026.
- The result itselfNot checkedWe quote it; we did not measure it.





