The use case: how Abnormal deploys CodeRabbit
Abnormal AI uses CodeRabbit to review pull requests before merge, acting 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 on human reviewers.
More reported results
Figures published in CodeRabbit’s case study. They are not independently measured by usedby.
Across Abnormal AI pull requests, CodeRabbit's acceptance rate for critical-severity comments is above 65%.
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.
Managing about 250 engineers, Shrivu Shankar, VP of AI Strategy at Abnormal AI, works across product and engineering to determine how AI should be applied throughout the company’s systems.
In the customer’s words
CodeRabbit provided a consistent enforcement layer both for AI-generated code and for engineers still writing code manually.Other AI tools used by Abnormal
Other public relationships recorded on usedby.
Explore Abnormal’s AI stackCodeRabbit users in Cybersecurity
Companies in the same sector, with public evidence.
See all CodeRabbit customersGo straight to the source
Based on CodeRabbit’s published case study. We check the public evidence; the results are reported by the vendor.
coderabbit.ai- Last checked
- Nov 10, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 100 hoursChecked
Printed word for word on the page, near the name of Abnormal.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Abnormal.
- Abnormal uses CodeRabbitChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
In the last 30 days alone, CodeRabbit has saved an estimated 100 hours of reviewer time, increasing review throughput without compromising human validation.







