The AI Record
That is fast enough that most engineers see the review comment before they have finished context-switching to another task. The metric we’re the proudest about, though, is that engineers have only needed to “break glass” 288 times (0.6% of merge requests).

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

Post: Orchestrating AI Code Review at scale, Cloudflare blog, April 20, 2026, at Show me the numbers! / The overview.

  • 288 break glass overrides, March 10 to April 9, 2026. No person in the loop

Checked against the source [ Grade B ] Said in the last year Cloudflare: $2.2 billion revenue, FY2025 Sells AI tools

Filed under

Who is speaking

Ryan Skidmore, Author of Cloudflare's "Orchestrating AI Code Review at scale" blog post. Wrote the engineering post describing the system Cloudflare runs internally, with its own usage data.

Cloudflare sells AI or agent tools or services, so it has a reason to publish flattering numbers about AI. The passage stays in the archive; read it with that in mind.

How this was checked

Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Claude Sonnet), blind second pass from passage text and citation only, no repository access, 2026-11-04).

Verbatim, with the page's curly apostrophe in 'we’re' and curly quotes around 'break glass' (allowed normalization). The passage sentence follows directly after the 3m39s sentence. Author is Ryan Skidmore.

How to cite this passage

Ryan Skidmore (Cloudflare), “Orchestrating AI Code Review at scale”, Cloudflare blog, 2026-04-20, at Show me the numbers! / The overview. https://blog.cloudflare.com/ai-code-review Archived at https://the-ai-record.com/passages/cloudflare-metric-we-re-proudest-though-engineers-2026

More from the same source

The bias is explicitly toward approval, meaning a single warning in an otherwise clean MR still gets approved_with_comments rather than a block.

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

Post: Orchestrating AI Code Review at scale, Cloudflare blog, April 20, 2026, at The coordinator helps keep things focused.

Checked against the source [ Grade B ] Said in the last year Cloudflare: $2.2 billion revenue, FY2025 Sells AI tools Passage page

On the cost side, the average review costs $1.19 and the median is $0.98. The distribution has a long tail of expensive reviews – massive refactors that trigger full-tier orchestration. The P99 review costs $4.45, which means 99% of reviews come in under five dollars.

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

Post: Orchestrating AI Code Review at scale, Cloudflare blog, April 20, 2026, at Show me the numbers! / The overview.

  • $1.19 cost per review, average, March 10 to April 9, 2026

Checked against the source [ Grade B ] Said in the last year Cloudflare: $2.2 billion revenue, FY2025 Sells AI tools Passage page

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

Post: Orchestrating AI Code Review at scale, Cloudflare blog, April 20, 2026, at Show me the numbers! / The overview.

  • 131,246 review runs, first 30 days, March 10 to April 9, 2026. A person approves
  • 219 seconds median review time, March 10 to April 9, 2026. A person approves

Checked against the source [ Grade B ] Said in the last year Cloudflare: $2.2 billion revenue, FY2025 Sells AI tools Passage page

We've been running this system internally across tens of thousands of merge requests. It approves clean code, flags real bugs with impressive accuracy, and actively blocks merges when it finds genuine, serious problems or security vulnerabilities.

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

Post: Orchestrating AI Code Review at scale, Cloudflare blog, April 20, 2026, at Introduction.

Checked against the source [ Grade B ] Said in the last year Cloudflare: $2.2 billion revenue, FY2025 Sells AI tools Passage page

Today, when an engineer at Cloudflare opens a merge request, it gets an initial pass from a coordinated smörgåsbord of AI agents. Rather than relying on one model with a massive, generic prompt, we launch up to seven specialised reviewers covering security, performance, code quality, documentation, release management, and compliance with our internal Engineering Codex. These specialists are managed by a coordinator agent that deduplicates their findings, judges the actual severity of the issues, and posts a single structured review comment.

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

Context. Describes the system as deployed on internal merge requests.

Post: Orchestrating AI Code Review at scale, Cloudflare blog, April 20, 2026, at Introduction.

Checked against the source [ Grade B ] Said in the last year Cloudflare: $2.2 billion revenue, FY2025 Sells AI tools Passage page

Something wrong? Report a correction. JSON: /api/v1/passages/cloudflare-metric-we-re-proudest-though-engineers-2026.json