# How Abnormal uses CodeRabbit

**100 hours**: “In the last 30 days alone, CodeRabbit has saved an estimated 100 hours of reviewer time”

As published on [coderabbit.ai](https://www.coderabbit.ai/case-studies/how-abnormal-ai-scales-autonomous-development-with-coderabbit). Captured by usedby on 2026-10-06.

- Company: [Abnormal](https://www.usedby.ai/companies/abnormal.md)
- Tool: [CodeRabbit](https://www.usedby.ai/tools/coderabbit.md)
- Industry: [Cybersecurity](https://www.usedby.ai/companies/industry/cybersecurity.md)
- Teams: Engineering

## What the story says

Abnormal AI uses CodeRabbit to review pull requests before merge as an enforcement layer for both AI-generated and manually written code. It automatically ingests the company's markdown documentation to apply internal policies and flag issues that would otherwise fall to human reviewers.

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

> In the last 30 days alone, CodeRabbit has saved an estimated 100 hours of reviewer time, increasing review throughput without compromising human validation.

- **65%**: “Across Abnormal AI pull requests, CodeRabbit's acceptance rate for critical-severity comments is above 65%.”
- **54%**: “That performance translates into measurable impact across high-risk domains, with acceptance rates of 54% for functional correctness, 52% for data integrity and integration and over 40% for security and privacy.”

> CodeRabbit provided a consistent enforcement layer both for AI-generated code and for engineers still writing code manually.
>
> Shrivu Shankar, VP of AI Strategy

## What usedby checked

We compared the story with its live page on 2026-10-06.

- Checked: the figure 100 hours is printed word for word on the page, near the name of Abnormal.
- Checked: the passage quoted above is copied word for word from the page, near the name of Abnormal.
- Checked: Abnormal uses CodeRabbit. Confirmed line. Latest check across sources: 2026-10-06.
- Not checked: the result itself. We quote it; we did not measure it.

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