Agent review: 36 sourced coding agent stories
A separate agent or a different model reviews, audits or tries to break each change. This technique sits in the Review and merge stage. Of the 36 stories, 6 were published by a tool vendor and 30 by the people who did the work. 23 involve an existing codebase and 10 started from scratch. Every number links to where it was published.
Keboola: a two-sentence prompt to Claude Code merges 13 Zend-removal PRs in about 22 hours through an existing agent harness
Keboola · Claude Code
CaveatsWritten by the engineer who ran the experiment, on his personal blog; he does not state his role at Keboola. The merged changes were small. The harness was built beforehand and the post does not say how long that took. The 56-dependency figure appears in the post without saying whether it was all from this run. Overnight PRs waited 10–13 hours for review, and the E2E queue and human approvals were the main slowdowns. One task duplicated already-merged work after the agent read a stale local main.
13 in about 22 hours (3 more open)
Merged PRs
Christopher Weir coordinates about 90 Claude Code worker sessions from one "ringleader" thread for more than 60 merged PRs in five weeks
Christopher Weir · Claude Code
CaveatsSelf-reported by the developer about a work codebase; the company, product, stack and the kind of change behind the 60+ PRs are not named, so the work type is uncertain (the only named project is a later navigation refactor). Figures are rounded on purpose. He has not measured total cost or elapsed time against doing the project in one thread. In one case parallel workers filled the disk and stopped the local container runtime.
About 90 Claude Code sessions
Worker sessions
QuEra: one engineer with Cursor and Claude Code merges 111 PRs across 19 repos, empty repo to merged service in six days
QuEra · Cursor, Claude Code, Quantopus (QuEra)
CaveatsSelf-reported by QuEra. The 111-PR results come from interactive Cursor and Claude Code sessions by one engineer, not from unattended Quantopus runs, and the post keeps the two apart. QuEra itself says the $3,900 excludes the engineer's time and infrastructure, prices Claude at API rates rather than the actual subscription and misses earlier usage, that the effort estimate has about ±50% uncertainty, that there is no comparable project to measure speedup, and that test results were not independently rerun. All 111 PRs were merged by the engineer; 54 also had peer review. No author is named.
111 across 19 repositories
Merged pull requests
Fergus ships 6.3× more weekly merges with the same-sized team, cutting PR merge time from 18 hours to 1.6
Fergus · Tool unstated
CaveatsSelf-reported by Fergus's engineering lead. The post does not name which coding agents or AI review tools they used. Throughput (up 500%) and weekly merges (6.3×) are related but separately stated; raw PR counts are not given. 6.3× overall vs 4.7× per author is explained as more merged PRs coming from outside the engineering team. They report a handful of outages even as change failure rate halved. Comparison window for the 6.3× figure is not dated beyond the same team size as 18 months ago.
6.3×, same sized Fergus Engineering team
Weekly code merges
Alexander Marquardt runs a coding-agent fleet that merged 1,652 pull requests in a month on an e-commerce search solution, with 0.2 to 0.7% later reverted
Alexander Marquardt (e-commerce search solution) · Claude Code
CaveatsSelf-reported by the engineer who runs the project, on his personal site; the employer and team size are not stated. Merged PR counts and line counts are throughput measures the author himself says are imperfect. The author says rework is about one fix round per merged PR, and he does not yet measure how many real shopper queries are interpreted correctly. Claude Code is named only in connection with hooks; the full set of agents and models is not stated.
1,652 (about 373 a week), median 492 changed lines
Merged PRs, main repo, October 2026
Operum: two founders running six-role AI agent teams merge 296 PRs in 12 days, each gated on an AI tester approving the exact commit
Operum · Operum
CaveatsWritten by a co-founder about building Operum with Operum, in a post leading into its Product Hunt launch, so it promotes the product. The PR categories come from titles, not a diff audit, and the author says the PRs are small and PR count is the wrong scoreboard. Cursor is named as the app's default engine and recommendation; the post does not say which engine the team used for these 296 PRs, so the tool is Unstated. Revert and rework rates are not reported.
296 in 12 days (15–26 Oct 2026)
Merged PRs
Microsoft's Copilot Cowork team goes empty-repo to worldwide GA in 4.5 months with agents writing most of the code, then ports the live runtime from Python to Rust
Microsoft (Copilot Cowork) · Tool unstated
CaveatsSelf-reported Microsoft eng post. The specific coding-agent product is not named (only “agents”). Latency gain partly attributed to moving the agent loop out of the container, not Rust alone. No cost-per-turn claim.
13 Jan to 16 Jun 2026 (~4.5 months)
Empty repo to worldwide GA
Spawn, a ten-person game engine startup, says its agent fleet shipped 77,000 substantial changes in 30 days on $3.1M of tokens
Spawn · Claude Code
CaveatsThese are the founder's own claims about the company they run, unverified, published as an X Article rather than a blog post. No code, dashboards or outside data back the numbers. The post defines a substantial change as one touching engine code or game logic but doesn't show how changes are counted. The revert rate covers the last year, not the 30-day window. The post says the team is ten people but also refers to five people working alongside the agents. The author is named only by X handle and display name (jacob).
X Article by Spawn's founder (@jsnnsa), "How I Built the Most AI-Pilled Company in the World"
77,000 substantial changes in the last 30 days, about 108 an hour
Changes shipped
X2 Labs founder rebuilds BZFlag as a multiplayer browser game with Claude Code in seven days, mostly overnight, with 2,421 tests
X2 Labs (George Purusniuc) · Claude Code
CaveatsSelf-reported by the builder on his own company's site. A hobby game, not a commercial product; the post does not report players, cost or token usage. Numbers are counted from the git history, plans and test runner on 28 October 2026. The game reuses BZFlag's rules and source as a specification.
7 days from first commit to public
Time
Solo developer ships Kempt, a signed and notarised macOS app with Stripe licensing, four days after the first commit, built mostly by Claude Code
Kempt (Yassir Halaoui) · Claude Code, OpenAI Codex
CaveatsSelf-reported by a consultant whose post ends with a contact address. No cost figures. No sales or user numbers yet.
First commit 13 Oct to 1.0 on 17 Oct 2026 (five calendar days)
Time
Kassebaum Engineering lets agents review and merge routine code: 136 PRs across four repos in ten days, with people merging the riskiest tier
Kassebaum Engineering (William R. Kassebaum) · Claude Code, Cursor, Grok CLI
CaveatsSmall firm writing about its own setup, and the post ends with a sales pitch. The author says they have no time-saved figure. No security scanning in CI yet, and the cross-model review panel is built but not live. Uses Grok-based agents, including a Grok Bot engineering agent.
136 across four repositories over ten days in October 2026
Merged PRs
Three people build Loft with coding agents over three months, then ship its open format 53 hours after the first commit
Loft · Claude Code, OpenAI Codex
CaveatsWritten by the company about its own product, which it sells as a way to run agents. No cost, token or code-size figures. The fast V2 release rested on three months of earlier V1 work.
3 people
Team
Claude Code team doubles merged pull requests from June to September while the revert rate falls by more than 40%, by moving most review to agents
Anthropic (Claude Code team) · Claude Code
CaveatsVendor post about its own product, which also promotes Code Review for Claude Code. No absolute PR counts, incident numbers or cost. About review and merging rather than one build.
claude.dev blog (Addy Osmani, Morgan Westlee Lunt, Qing Wang)
More than doubled from June to September
Merged PRs
Cockroach Labs' agent pipeline adds IBM Db2 support to its migration tool in under two days for $4,172 in tokens, then lands 1,238 PRs in five months
Cockroach Labs · Claude, MOLT Sinai (Cockroach Labs)
CaveatsSelf-reported on Cockroach Labs' own blog. The Db2 sprint ran in a mirror repo with no human review, and the authors say they are still confirming the Db2 support is correct. The Oracle comparison is against a 2024 human project of different scope, so the 164x and 38x figures are rough. Human approval was turned on for every merge after the first week.
"less than two days" vs 9 months for Oracle support in 2024
Db2 support time
An autonomous Claude Code agent ships 340+ production deploys behind a three-stage gate it cannot edit
Yureki Lab (dev.to author) · Claude Code
CaveatsSelf-reported by a single pseudonymous author on dev.to about one team and one system. The company, codebase size and traffic are not named, and none of the numbers are independently checked. The author says every incident the gate caught was a wrong answer ("None of them produced a single 5xx"); commenters point out a 5% canary over 10 minutes may miss low-volume regressions, and that the canary thresholds come from the deploy block the agent writes, so the agent still chooses how strict its own check is. No figures are given for the agent itself (token cost, time per task) or for how long the gate took to build.
"340+ production deploys with zero human-paged incidents" over six months
Deploys since the gate
LinkedIn's multi-agent AI code reviewer runs 79,000 reviews a week with 63.9% of suggestions accepted
LinkedIn · Tool unstated
CaveatsBuilder-written. The models and harnesses behind the subagents are not named. This is review of code, not agent-written code; acceptance was judged by an LLM evaluator on a 7-day sample.
79,000+ across 40,000+ PRs in 7,500+ repositories
Weekly reviews
An AI coding agent rips out a core invariant across 189 files of a 717,000-line TypeScript app in three days, with no human code review
Joel Abenhaim (AI Sovereign Labs) · AICode
CaveatsSelf-reported: the author built the codebase, ran the operation and wrote the paper, and his company (AI Sovereign Labs) designs and distributes the agent used, so this is partly vendor. Single case; the codebase is closed source, though the build and raw logs (in French) are published.
717,725 lines of TypeScript, 3,648 files
Codebase
Assembled auto-approves low-risk PRs with Codex and Claude Code reviewers, lifting PRs merged to 2.4× its pre-agent baseline
Assembled · OpenAI Codex, Claude Code, Devin, 143.dev (Assembled)
CaveatsSelf-reported by Assembled's CTO. The author calls these observational rollout results, not a randomized trial, and says the auto-reviewer doesn't get credit for every point. The window is short (three weeks after full-team launch), and the bug figures are explicitly too early to be conclusive. The pre-agent baseline period is not precisely dated, and no absolute PR counts are given. Category multipliers differ between the intro (bugfixes 3.7×, refactors 7.5×, features 2.5×) and the results list (refactoring 7.5×, test work 3.4×). The $3.57 per attempt is an estimate, not total spend. Codex and Claude Code are the reviewers; Devin is mentioned only for non-engineer PRs, and the agents that wrote most of the PRs are not broken down.
2.4× pre-agent baseline
PRs merged
Ambrook migrates its design system from Material UI to Base UI in just over two weeks with a graph of planner and worker agents
Ambrook · Claude Code, Niteshift
CaveatsWritten by the team that did the work. No cost in dollars is given. 'Without any major regressions' is their own assessment. Niteshift and Supercut are third-party tools they used; the post does not say whether Ambrook has a commercial relationship with them.
54,000 lines changed across 794 files
Change
Anthropic's Mike Krieger ports an internal Python tool to 165,000 lines of TypeScript over a weekend with hundreds of Claude Code agents
Anthropic (Mike Krieger) · Claude Code
CaveatsVendor-published Anthropic article about Anthropic’s own tools and staff. Exact calendar date of the weekend and the tool’s product name are not stated.
165,000 lines of TypeScript over a weekend
Output
Engineer ships 11 Flutter apps and games to both app stores in two months with Claude Code and Codex, on $40 a month
Seif Ibrahim · Claude Code, OpenAI Codex
CaveatsSelf-reported. The apps are small, offline games and utilities. No line counts or revenue figures.
11 on iOS and Android
Apps shipped
Claude plans and reviews, Codex builds: a production music site migrated from a React SPA to Next.js in 36 hours
Nik McFly · Claude, OpenAI Codex
CaveatsSelf-reported by the site owner on his own blog. A single, fairly small site. The post does not say which Claude product (Claude Code or chat) was used. A staging Docker build filled the server disk and briefly caused production API errors during the migration. The author notes the performance numbers are for this migration only.
36 hours
Migration time
Bun's 535,000-line Zig codebase is ported to Rust in 11 days by up to 64 parallel Claude Code agents
Bun (Oven / Anthropic) · Claude Code
CaveatsBun was acquired by Anthropic in December 2025 and the author works at Anthropic, so this is close to vendor-published. Used a pre-release Anthropic model (Claude Fable 5); tokens were not paid for. The time-without-AI figure is the author's own estimate. Output is a faithful port, not idiomatic Rust (about 4% of code sits inside unsafe blocks).
535,496 lines of Zig (excluding comments), 1,448 .zig files
Source size
Luke Lin ships Baohua, a bilingual story-sharing app for families, in about a month with Claude Code writing the code and Codex reviewing PRs
Baohua (Luke Lin) · Claude Code, OpenAI Codex, gstack
CaveatsSelf-reported by the builder. No user or revenue numbers. The post recommends tools by name (gstack, Venn AI).
April 1 to April 30, 2026
Time to ship
Intercom lets an AI agent approve 19% of pull requests, with 93% of PRs now agent-driven
Intercom · Claude
CaveatsSelf-reported by Intercom. The post names Claude as writing the code but not the exact tool or the models behind the review agent. Revert-rate comparison is observational: AI-approved PRs are filtered to be small, which may favour them.
Over 93% (two main codebases)
Agent-driven PRs
Cloudflare’s OpenCode-orchestrated AI code review runs 131k times across 5,169 repos in 30 days, median 3m 39s and $0.98
Cloudflare · OpenCode
CaveatsSelf-reported Cloudflare engineering blog. This ships an AI review system, not application features; merge-quality impact beyond break-glass rate is not measured. Model names and costs are as of the March–April 2026 window.
131,246 review runs on 48,095 MRs across 5,169 repos
30-day volume
A solo developer ships an open-source social media management platform with 12 API integrations in three weeks, with Claude Code building and Codex reviewing
Brightbean (Jan Schu) · Claude Code, OpenAI Codex
CaveatsSelf-reported in a Show HN post and comments. No line counts, user numbers or dollar costs given. He says UX polish took most of the time ('80% of features worked in 20% of the time'). Some commenters questioned AI-written docs and comments.
3 weeks (plus 4 full days on specs)
Build time
Atlassian's Rovo Dev code review agent cuts median PR cycle time 30.8% across 1,900+ internal repositories in a year-long evaluation
Atlassian · Rovo Dev
CaveatsAtlassian sells Rovo Dev, so this is vendor-published, though the evaluation was accepted at ICSE 2026. It is a review agent, not one that writes the code. Cycle-time change is observational over adoption, not a controlled comparison.
Over a year across 1,900+ repositories
Scope
Cloudflare engineer rebuilds the Next.js API surface on Vite in under a week with Claude in OpenCode, for about $1,100 in tokens
Cloudflare · OpenCode
CaveatsWritten by the engineer who did the work, on the company blog, at launch. vinext is labelled experimental and "not yet been battle-tested with any meaningful traffic at scale". Benchmarks use a single 33-route app and measure compilation and bundling, not serving performance; the post says to treat them as directional. Static pre-rendering at build time was not supported at launch. The post says some AI PRs "were just wrong" and needed regular course correction. Exact model versions are not named.
Under a week; first commit 13 February
Time
Ladybird ports its JavaScript engine's parser and bytecode compiler from C++ to Rust in two weeks with Claude Code and Codex
Ladybird · Claude Code, OpenAI Codex
CaveatsSelf-reported by the project founder. Not autonomous: the author decided what to port, in what order and how the Rust should look. The code is intentionally non-idiomatic Rust that mirrors the C++. No cost or token figures given.
About 25,000 lines of Rust
Output size
OpenAI team ships an internal product with zero hand-written code: ~1M lines and ~1,500 merged PRs in five months with Codex
OpenAI · OpenAI Codex
CaveatsWritten by the vendor about its own tool. Line count includes docs and tooling. No cost, time-vs-estimate or quality figures.
~5 months
Duration
Fullscript's Nitro background agent creates 19% of pull requests three months after launch on a decade-old Rails monolith
Fullscript · Claude Code, Nitro
CaveatsSelf-reported. No absolute PR counts, merge rates or quality metrics beyond one reverted N+1 fix that caused production 500s. Every PR still needs human review, CI and E2E tests.
19% in January 2026, three months after launch
Share of PRs created by Nitro
Vellum's 15 engineers double monthly PRs from 946 to 1,910 with background agents and Codex as first-pass reviewer
Vellum · Devin, OpenAI Codex, Cursor, Claude Code
CaveatsSelf-reported on Vellum's company blog, which also promotes a webinar with Cognition (maker of Devin). PR counts compare one month with another; PR size and quality are not measured. The year of the May baseline is 2024 per the post; the October figure's year is not stated explicitly. Humans review post-merge rather than before merge, so Codex review is the main pre-merge gate.
946 in May → 1,910 in October
PRs
Uber's uReview AI code reviewer covers over 90% of ~65,000 weekly diffs, with 75% of comments rated useful
Uber · uReview (Uber)
CaveatsSelf-reported by Uber. This is an AI code reviewer, not an agent that writes code, and the post gives no merge-rate, cycle-time or defect outcomes. It does not say which coding agents authored the reviewed diffs, so the tool is Unstated. Published August 2025, earlier than Uber's other stories on the site. Volume figures are inconsistent: '~65,000' diffs is called weekly in one place and 'per month' in another, and 'over 90%' coverage sits awkwardly with 'over 10,000 commits' processed a week. The 1,500 hours a week is an estimate assuming a second human reviewer needs 10 minutes per commit. The usefulness rate counts only engineers who rate comments. Fixer, the companion tool that proposes code changes, is not covered.
Uber Engineering blog (Sonal Mahajan, Shauvik Roy Choudhary, Will Bond)
Over 90% of ~65,000 weekly diffs landed
Coverage
Pieter Levels builds a browser flight sim with Cursor in ~3 hours; it hits $1M ARR in 17 days
Pieter Levels (indie maker) · Cursor
CaveatsSelf-reported on X. Revenue is from in-game ads and sponsors and owes a lot to the author's large existing audience, so it says little about the code. By his own account the build 'didn't go 100% smooth', with about 80% going well. A single large file slowed edits (15 seconds per change) and caused Cursor issues. MRR at a launch-hype peak isn't sustained revenue. Third-party posts also credit Grok 3 and other tools.
~3 hours (author's estimate)
Time to first playable version
Satispay modernizes its core payment service from Java 8 to Java 21 and Spring in under four days with Claude Code, against a four-week estimate
Satispay · Claude Code
CaveatsAnthropic customer marketing page. No publish date on the page. No independent verification of the four-day migration, defect rates, or the 75% code-share metric. CTO quotes selected by the vendor.
Under 4 days vs 4-week estimate (Java 8 → 21 + Spring)
Core payment modernization