# How Prokeep uses CodeRabbit

**4.29 days**: “4.29 days of reviewer time saved in the first three months”

As published on [coderabbit.ai](https://www.coderabbit.ai/case-studies/how-prokeep-catches-breaking-changes-and-scales-ai-code-review-with-coderabbit). Captured by usedby on 2026-10-08.

- Company: [Prokeep](https://www.usedby.ai/companies/prokeep.md)
- Tool: [CodeRabbit](https://www.usedby.ai/tools/coderabbit.md)
- Teams: Engineering

## What the story says

Prokeep's engineering team uses CodeRabbit to give every GitLab merge request an independent first-pass AI review before two required human approvals. It checks changes for bugs, risks, and edge cases, including database migration safety.

Summary written by usedby from the source page, in English. The figures are those of CodeRabbit and Prokeep, not ours.

> CodeRabbit also estimated that it saved 4.29 days of reviewer time during that period. For a team of roughly two dozen engineers, that reclaimed capacity matters as AI tools continue increasing the amount of code entering review.

- **69.8%**: “69.8% overall comment acceptance rate in the first three months”
- **79.4%**: “79.4% acceptance rate for functional-correctness comments”

> It is absolutely catching real issues at review time that humans are not.
>
> Liz Baker, Senior Engineering Manager at Prokeep

Source: [coderabbit.ai](https://www.coderabbit.ai/case-studies/how-prokeep-catches-breaking-changes-and-scales-ai-code-review-with-coderabbit), captured 2026-10-08.

## What usedby checked

We compared the story with its live page on 2026-10-08.

- Checked: the figure 4.29 days is printed word for word on the page, near the name of Prokeep.
- Checked: the passage quoted above is copied word for word from the page, near the name of Prokeep.
- Checked: Prokeep uses CodeRabbit. Confirmed line. Latest check across sources: 2026-10-08.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/prokeep-coderabbit · How we check: https://www.usedby.ai/methodology