Source proof for Cloudflare runs a multi-agent AI code reviewer on merge requests across 5,169 repositories

…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 f…

…oks like across 5,169 repositories from March 10 to April 9, 2026. The overview 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 r…

…lex codebases. Instead of building a monolithic code review agent from scratch, we decided to build a CI-native orchestration system around OpenCode , an open-source coding agent. Today, when an engineer at Cloudflare opens a merge request, it gets an initial…

…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 f…

…t AI agents burning Opus-tier tokens to review a one-line typo fix in a README. The system classifies every MR into one of three risk tiers based on the size and nature of the diff: // Simplified from packages/core/src/risk.ts function assessRiskTier ( diffEnt…

…model calls. Each model tier has independent health tracking with three states: When a model's circuit opens, the system walks a failback chain to find a healthy alternative. For example: const DEFAULT_FAILBACK_CHAIN = { "opus-4-7" : "opus-4-6" , // Fall…

…oks like across 5,169 repositories from March 10 to April 9, 2026. The overview 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 r…

…7 times (the initial review, plus re-reviews as the engineer pushes fixes), and the median review completes in 3 minutes and 39 seconds . That is fast enough that most engineers see the review comment before they ha…

…y needed to “break glass” 288 times (0.6% of merge requests). 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…

Orchestrating AI Code Review at scale | Cloudflare Blog Skip to content All Categories AI Developers Radar Product News Security Policy…

…a CI-native orchestration system around OpenCode , an open-source coding agent. 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 t…

…of nitpicks about variable naming, the author responds, and the cycle repeats. Across our internal projects, the median wait time for a first review was often measured in hours. When we first started experimenting with AI code review, we took the path that…

…ty! Unfortunately, though, the one recurring theme that kept coming up was that they just didn’t offer enough flexibility and customisation for an organisation the size of Cloudflare. So, we jumped to the next most obvious path, which was to grab a git diff, sho…

…shove it into a half-baked prompt, and ask a large language model to find bugs. The results were exactly as noisy as you might expect, with a flood of vague suggestions, hallucinated syntax errors, and helpful adv…

…lex codebases. Instead of building a monolithic code review agent from scratch, we decided to build a CI-native orchestration system around OpenCode , an open-source coding agent. Today, when an engineer at Cloudflare opens a merge request, it gets an initial…

…tation, 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. We've been running this system internally across tens of thousands of merge req…

…t AI agents burning Opus-tier tokens to review a one-line typo fix in a README. The system classifies every MR into one of three risk tiers based on the size and nature of the diff: // Simplified from packages/core/src/risk.ts function assessRiskTier ( diffEnt…

…model calls. Each model tier has independent health tracking with three states: When a model's circuit opens, the system walks a failback chain to find a healthy alternative. For example: const DEFAULT_FAILBACK_CHAIN = { "opus-4-7" : "opus-4-6" , // Fall…

…oks like across 5,169 repositories from March 10 to April 9, 2026. The overview 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 r…

…7 times (the initial review, plus re-reviews as the engineer pushes fixes), and the median review completes in 3 minutes and 39 seconds . That is fast enough that most engineers see the review comment before they ha…

…y needed to “break glass” 288 times (0.6% of merge requests). 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…

…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). On the cost side, the average review costs $1.19 and the median is $0.98 . The…

…urce coding agent. 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…

…oks like across 5,169 repositories from March 10 to April 9, 2026. The overview 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 r…

…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. This is just one of the many ways we’re improving our engineering resiliency as…