How is AI used in code review?

“93% of our PRs are now automatically handled by Review Buddy so that the highest quality engineers are spending time on the 7% of PRs that truly matter,”

Geoff CharlesChief Product Officer (CPO) · Executive, Ramp

“uReview today analyzes over 90% of the weekly ~65,000 diffs (equivalent of pull requests) landed at Uber. Engineers who interact with the tool mark 75% of its comments as useful”

Sonal MahajanStaff Engineer, Programming Systems team · Practitioner, Uber

“We're now seeing agentic code reviews that look at code changes through a series of different lenses. In the past, it would have been impractical for a cloud infrastructure engineer and a security engineer to review every single code change. With agents, that becomes possible.”

Venkat VenkataramaniVP of Engineering, Applied Infra · Leader, OpenAI

“The reviewer agent surfaces issues and inconsistencies; the human makes the final call on quality and correctness.”

WarpPublished by the organization itself (documentation), no named author

“It finds the right human reviewer to loop in.”

Geoff CharlesChief Product Officer (CPO) · Executive, Ramp

“a growing share of sessions aren’t initiated by humans, but by automated managed agents handling code review, self-healing CI failures, completing E2E PRs with visual validation, triaging on-call alerts, debugging incoming bugs, and handling a variety of code maintenance tasks with human reviews/escalations.”

Uday Kiran MedisettyDistinguished Engineer · Practitioner, Uber

“if this is an autonomous diff coming from Minion, we want to give a human reviewer some confidence that this diff has gone through a lot of self-improvement already”

Uday Kiran MedisettyDistinguished Engineer · Practitioner, Uber

“Mode · Automation: PR review. Durable session, woken by an external system, often no human in the loop.”

Burke LibbeyPrincipal Engineer · Practitioner, Shopify

“Over the last 30 days: 100% AI code reviewer coverage across all repos on our standard CI pipeline.”

CloudflarePublished by the organization itself (post), no named author

“code reviewed over 50,000 pull requests authored by humans”

HubSpotPublished by the organization itself (post), no named author

“We are definitely still bottlenecked on reviews, especially for things that are touching some architecture pieces. And it's actually more subtle than just being bottlenecked on review, … we can carve out time differently. It's … bottlenecked on human ability to even fully conceptualize what we're doing.”

Mike KriegerHead of Anthropic Labs · Leader, Anthropic

“actually talked to Claude about the code and say, all right, these are the questions that I would have. Can you go investigate it? So it is kind of … code review, but still human-driven, and for the really important ones. And for the ones that are cosmetic visual changes, it's much more like we'll fix forward if we need to fix forward.”

Mike KriegerHead of Anthropic Labs · Leader, Anthropic

“So one of the reasons we built … artifacts that we shipped a couple of weeks ago was partially for that, which is you would send somebody a PR, and then they'd be like, I don't know, man, this is like 2000 lines of code. It looks like code to me. And what we started doing instead is sharing much more like, here's a … artifact. Here's the explanation. Here's the intention of the change. Here's the trade-offs that were made.”

Mike KriegerHead of Anthropic Labs · Leader, Anthropic

“You get a pretty high degree of confidence on merge. Today, almost a fifth of all the pull … are merged without any human review or without any human testing. … that is a number that we care a lot about and want to bring higher and higher, of course, within the guardrails of producing really high quality code.”

Daksh GuptaCo-founder · Executive, Greptile

“So there didn't seem to be very big difference between the rate at which pull requests were reverted from people versus agents in my study.”

Daksh GuptaCo-founder · Executive, Greptile

“every time there's a pull request, we have a swarm of agents. And they go and look at every file that's changed, every file that's related to the files that change to figure out if there's bugs. And it also spins up your code in a sandbox, … dependencies, spins up local host, clicks around to try to break things, mocks inputs, and everything else to figure out if the code is broken.”

Daksh GuptaCo-founder · Executive, Greptile

“So then I started tracking the counts of P0s, P1s, and P2s in all of these changes. And interestingly, once again, there was not that much of a difference. In fact, three out of the four agents that we tested performed better than humans in terms of the rate at which … were producing P0s. They were producing fewer P0s than humans were. Similarly, the case with P1s and P2s. Broadly speaking, human-generated PRs were about equal in quality to … PRs based on this data.”

Daksh GuptaCo-founder · Executive, Greptile

“And so I started tracking the number of iterations, the number of review rounds between when the pull request was opened and when it was merged. Sure enough, very little difference. … Once again, very little if any statistical difference between human-generated and AI-generated pull requests in terms of how many iterations before they're ready to merge.”

Daksh GuptaCo-founder · Executive, Greptile

“we've decided we always, every PR description will start with something like that, something that I wrote by hand … could be very short to describe what this is doing and what this is doing.”

Eyal BlumSoftware Engineer · Practitioner, Figma

“This tool basically visualizes our dependency graph internally with some external dependencies as well, … But what's more interesting is we can go build CLI tools that guarantee that certain invariants can't be broken. And what this does is when Claude builds a new package or adds a dependency that's leaky, we now have CI/CD changing or a simple git commit history that tells us exactly where things break. And by this, we're actually able to make our architecture change. We haven't changed our architecture in the last three or four months.”

Vaibhav GuptaCo-founder and Chief Executive · Executive, Boundary (BoundaryML)

“We do no code reviews. We require every engineer to work on things in parallel, and we have no standardization how people do AI.”

Vaibhav GuptaCo-founder and Chief Executive · Executive, Boundary (BoundaryML)

“I think we found that the state-of-the-art in December was you can probably, run this for about two weeks. By the end of those two weeks, you’d find that, hey, you want to, change the color of a button. Well, it turns out this button is implemented in, 10 different places, and they, have All these different variations, and oh, you forgot one of them, and actually it’s a slightly different color in one spot.”

Walden YanCo-founder and Chief Product Officer · Executive, Cognition

“Back in 2024, we were seeing that engineers would get their first review within three hours. Now, in 2026, that has grown to nine hours, in addition to all of the volume changes. So in short, code review is now the bottleneck that we are running into.”

Will BondStaff Engineer, AI Foundations team, Development Platform organization · Practitioner, Uber

“Currently, we still have humans approving the code, but we see a short path in the near future to a percentage of our code landing automatically, having automatic approvals, right?”

Will BondStaff Engineer, AI Foundations team, Development Platform organization · Practitioner, Uber

“One of the biggest learnings in this process was like the model doesn't know that it's wrong. It always confidently says 100% sure that, yeah, this is the review for your code. Go ahead. But we saw that, no, it actually needs a lot of guidance from the teams, because each team has its own style guide, its own patterns or … anti-patterns that they want to look for.”

Ameya KetkarSpeaker, AI Engineer World's Fair 2026 (job title not stated) · Practitioner, Uber

“One thing that we learned is that actually writing the skill was very easy, like teams just very quickly wrote a skill by asking Claude to write one, go over my previous PR reviews and write me a skill, but the hard part was how to run these skills at scale with consistent quality and low cost, and that required a lot of iterations, not only from the [uReview] team side, but also … for each team who was trying to write these rules.”

Ameya KetkarSpeaker, AI Engineer World's Fair 2026 (job title not stated) · Practitioner, Uber

“But rather than killing the outer loop, I think that we believe and the industry has just started to really kind of coalesce on this idea that … really expanding the outer loop. Rather than removing humans from the code review process, we are moving their responsibilities up a layer.”

Will BondStaff Engineer, AI Foundations team, Development Platform organization · Practitioner, Uber

“Uber spent the time to invest in building an in-house solution due to some of the constraints that we have. One of those is we currently use [Phabricator] and have for a long time and are in the process of migrating to GitHub. Most of the solutions do not provide support for [Phabricator].”

Will BondStaff Engineer, AI Foundations team, Development Platform organization · Practitioner, Uber

“[uReview] does … around 25,000 comments a week, and we get 10% of them actually get some feedback … We also saw that the overall address rate was around 67%, and almost three quarters of the high severity issues were usually addressed by the developers”

Ameya KetkarSpeaker, AI Engineer World's Fair 2026 (job title not stated) · Practitioner, Uber

“we saw that against like a very naive implementation, our costs were down by 60%, and our quality and our accuracy was up by around 70%.”

Ameya KetkarSpeaker, AI Engineer World's Fair 2026 (job title not stated) · Practitioner, Uber

“engineers don't trust AI opinions. They just trust clear findings tied to standards that we … agreed upon. … it stopped sounding more like, maybe this is a problem and started sounding more like this violates a standard that we actually care about.”

Rajesh BhatiaSenior Director of Engineering, Cloudflare · Leader, Cloudflare

“Our Network Firewall team audited rampartd using a multi-agent consensus process where every requirement was scored COMPLIANT, PARTIAL, or NON-COMPLIANT with specific violation details and remediation steps reducing what previously required weeks of manual work to a structured, repeatable process.”

CloudflarePublished by the organization itself (post), no named author

“As of June 2025, 80% of our engineers and data scientists connected to their work software an AI copilot that can create and review code”

KlarnaPublished by the organization itself (regulatory filing), no named author