Search the archive

“We run Code Review on nearly every PR at Anthropic. Before, 16% of PRs got substantive review comments. Now 54% do. It won't approve PRs — that's still a human call — but it closes the gap so reviewers can actually cover what's shipping.”

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

“Findings get verified by other agents before humans review them. Several agents look for bugs at the same time. Then a separate group votes on each finding, and it only gets posted if enough of them agree it's real. Findings that are only about style, diagnostics, or cleanup get dropped. We A/B tested those filters on our own PRs before keeping them.”

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

“Reviews are billed on token usage and generally average $15–25, scaling with PR size and complexity.”

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

“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 already had Ona's code review automation running on every PR. The agent reviewed diffs, ran the code in a full environment, cross-referenced tickets, and left inline comments with an 88% acceptance rate and a 50% reduction in time spent on pull requests.”

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

“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

“As we ship more code with agents, the bottleneck shifted from writing code to reviewing it. Devin Review turns large, complex GitHub PRs into intuitively organized diffs and precise explanations. We use it for every PR now.”

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

“This AI Assistant started as an internal experiment and now has scaled to support over 90% of PRs across the company impacting more than 600K pull requests per month.”

Sneha TuliPrincipal Product Manager · Leader, Microsoft

“After 6 months in production: 70% reduction in trivial review comments (style, formatting) 40% faster PR turnaround time Zero security issues missed in production (caught during review) $0.12 average cost per PR review (using cost-optimized model routing)”

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

“Per early experiments and data science studies, 5000 repositories onboarded to AI code reviewer observed 10 – 20% median PR completion time improvements.”

Sneha TuliPrincipal Product Manager · Leader, Microsoft

“In the first 30 days, the system completed 131,246 review runs across 48,095 merge requests in 5,169 repositories. The average merge request gets reviewed 2.7 times (the initial review, plus re-reviews as the engineer pushes fixes), and the median review completes in 3 minutes and 39 seconds.”

Ryan SkidmoreAuthor of Cloudflare's "Orchestrating AI Code Review at scale" blog post · Practitioner, Cloudflare

“[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

“Rovo Dev is an LLM-powered agent that can review pull requests and post actionable suggestions to accelerate merges and deployments. It targets issues developers most often act on, i.e., readability, bugs, and maintainability, and formats each suggestion so authors can apply the in-line changes by just one click.”

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

“offers the promise of accelerating feedback cycles (i.e., decreasing the PR cycle time by 30.8%), alleviating reviewer workload (i.e., reducing the number of human-written comments by 35.6%), and improving overall software quality (i.e., finding errors with actionable suggestions).”

AtlassianPublished by the organization itself (paper), no named author

“Our most successful example of this has been review buddy, our code review agent. It started with engineers on another team hooking up a GitHub webhook to Inspect's API with a review-oriented prompt. They could just focus on making the code review part great while we provided them all the infrastructure to actually run this agent. Now, review buddy runs on every pull request at Ramp, and we've replaced all of our third-party code review tools.”

Zach BruggemanPrincipal engineer, Ramp · Practitioner, Ramp

“Any incidents are now an eval. The team collected past PRs that caused incidents, with their fix-forwards and reverts, and had engineers who know that code confirm each bug and where it lived. The reviewer runs against that set daily.”

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

“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

“The builder verifies with targeted checks and runs a quick self-review. CI runs the deterministic harness. The deep review runs on request in an independent session, with the verdict returned to whoever asked. The author's watch loop handles threads and formal re-requests. Humans own the required approvals, and bot or agent verdicts do not satisfy them.”

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

“Approximately 1 million automated code reviews completed by Citi’s Generative AI tools year-to-date, saving approximately 100,000 hours per week across Citi’s developer population”

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

“Our PR review Agent doesn’t treat code review as a single task. It decomposes it into separate sub-jobs, each handled by an independent sub-Agent. One assesses the quality of the problem description. Another checks whether the diff actually aligns with the stated intent. Another reviews for safety concerns. Another checks for logical correctness. Another reviews against best practices and known anti-patterns.”

Intercom (renamed Fin in May 2026)Published by the organization itself (post), no named author