65.4%
“Over six months, Nursa engineers accepted 65.4% of CodeRabbit's comments.”
As published on coderabbit.ai. Captured by usedby on Oct 8, 2026.
What happened
Nursa's engineering team uses CodeRabbit as an automated pull-request reviewer for AI-generated code, replacing a required SonarQube Cloud quality gate. It provides baseline contextual review on every PR while humans keep control over architecture, business rules, and sensitive areas.
Summary written by usedby from the source page, in English. The figures are those of CodeRabbit and Nursa, not ours.
- seven out of ten“When CodeRabbit flagged a serious issue, the team acted on seven out of ten findings.”
- 20 minutes“The separate CI step added about 20 minutes, and unrelated merges could change the analysis result.”
CodeRabbit became part of the verification system that lets Nursa ship AI-generated code at production speed while preserving human judgment over architecture, business rules, and sensitive areas.
We increased the size of our PRs. Generating code is so cheap, and being able to review more at the same time is what CodeRabbit gives us.
What the story claims, and what we checked
We compared the story with its live page on Oct 8, 2026.
- The figure: 65.4%CheckedPrinted word for word on the page, near the name of Nursa.
- The passage quoted aboveCheckedCopied word for word from the page, near the name of Nursa.
- Nursa uses CodeRabbitCheckedConfirmed line. Latest check across sources: Oct 8, 2026.
- The result itselfNot checkedWe quote it; we did not measure it.




