The use case: how CodeRabbit deploys Exa
CodeRabbit, an AI code review platform, uses Exa's Search API with deep search to verify review comments against external context such as library versions, API changes, docs, changelogs, and commits. It replaces multiple repeated web-search calls with a single agentic call, and runs only when a review needs outside context.
More reported results
Figures published in Exa’s case study. They are not independently measured by usedby.
Exa Search: P50 7.1 seconds and P95 11.1 seconds.
In a four-day sample, web search ran for 7-10% of PRs on a given day.
With the prior agentic web search provider, Deep Search-style checks could require multiple calls and take about 30-45 seconds.
In the customer’s words
Exa consistently shows higher quality than other AI search providers we tested. What Exa is able to do in 1 search took our old provider multiple searches, taking 5 times as long.Other AI tools used by CodeRabbit
Other public relationships recorded on usedby.
Explore CodeRabbit’s AI stack
Exa users in DevTools & Infrastructure
Companies in the same sector, with public evidence.
See all Exa customers
Go straight to the source
Based on Exa’s published case study. We check the public evidence; the results are reported by the vendor.
exa.ai- Last checked
- Nov 12, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 70-75%Checked
Printed word for word on the page, near the name of CodeRabbit.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of CodeRabbit.
- CodeRabbit uses ExaChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Prior to using Exa, that verification often required several search calls. Switching to Exa Search cut CodeRabbit's web-search volume by about 70-75% while preserving, and sometimes improving, review quality.