Rules, skills and context files: 65 sourced coding agent stories
The agent is steered with written instructions and context: AGENTS.md/CLAUDE.md, skill files, rule docs, migration guides, golden examples, indexed code or telemetry. This technique sits in the Context stage. Of the 65 stories, 13 were published by a tool vendor, 51 by the people who did the work and 1 by independent researchers or press. 45 involve an existing codebase and 16 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
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
Dropbox engineers use coding agents to ship 22 accessibility features and clear a test cleanup deferred for two quarters in one week for the new Dropbox launch
Dropbox · Tool unstated
CaveatsWritten by Dropbox engineers about their own launch. The post does not name the coding agents or models, and gives no counts of PRs, lines or time saved beyond the cleanup week. Some work described (tracing dependencies, writing adapters) is AI-assisted rather than delegated to agents.
Dropbox Tech blog (Pravi Garg, Sourabh Yerfule, Gennadiy Civil)
22 across Home, All Files, file previews and Photos
Accessibility features
Duolingo builds AI STR Fix on the Claude Agent SDK to investigate and fix shake-to-report bugs, including release blockers
Duolingo · Claude Agent SDK
CaveatsWritten by Duolingo's DevX AI team about its own tool. No counts are given for tickets processed, fixes merged, success rate or cost. "Hours of manual work" per ticket is stated without a measured figure. Platforms are implied (Android and iOS experiments) rather than listed as a stack.
Has fixed release-blocking bugs
Outcome
Bloomberg's Automated Uplift ran LLM-assisted migrations across thousands of repositories: 2,333 PRs and 729 successful migrations
Bloomberg · Tool unstated
CaveatsWritten mostly by Bloomberg engineers who ran the work, with an academic co-author. Drafted from the abstract only; the abstract names no model or coding tool and gives no time or cost figures. 729 successes out of 2,333 PRs means many PRs did not result in a migration.
2,333 generated across two campaigns
Pull requests
University of Tokyo researchers port the NICAM climate model from 140,000 lines of Fortran to 35,000 lines of C++/Kokkos with Claude Code, running 1.71x faster on GH200
University of Tokyo and NIES (NICAM) · Claude Code
CaveatsWritten by the researchers who did the port. The cost is an estimate at API list prices; they actually used a subscription plan. Human working hours were not recorded (instruction counts come from Claude Code's own logs), and days spent only on human review or cluster work are not in the 23-day count. Branches outside the selected configuration were not ported, and the authors credit NICAM's consistent, well-maintained Fortran for part of the smooth run. Human review and the subscription's five-hour usage limits were the main constraints.
~140,000 lines of Fortran analysed and ported into ~35,000 lines of C++/Kokkos
Code ported
Microsoft Intune engineer moves an enrollment service library to .NET 8 in 1.5 weeks against a six-week estimate with GitHub Copilot modernization
Microsoft (Intune) · GitHub Copilot
CaveatsMicrosoft writing about its own GitHub Copilot product in its Customer Zero series. Savings are against the team's own estimates. No line counts, defect or cost figures.
Estimated at about six weeks, done in one and a half (75% schedule reduction)
First library
MerciYanis rewrites its whole platform, about 250,000 lines across 10 repositories, in one day with one engineer and around 30 parallel agents
MerciYanis · Tool unstated
CaveatsWritten by the company's own CTO. The one day excludes the earlier work raising test coverage from an average of about 60% to 100%, which the post says took most of the time. Results are reported from the QA environment; no production figures. Coding tool not named. Stack not stated; the post's code sample looks like TypeScript and its diagram names PostgreSQL and Kafka, so check before filling it in.
Roughly 250,000 lines across 10 repositories
Scope
A Claude Code skill for booking gym classes becomes MyLocker, an App Store and Google Play app now run day to day by Codex, with 107 merged PRs
MyLocker (Michael Cutler) · Claude Code, OpenAI Codex
CaveatsSelf-reported by the builder. Analytics are off, so there are no user numbers. Unofficial app for one gym chain's members.
3 days
Backend cutover
Developer builds and ships the Tabby tab-manager browser extension in 19 days by talking to Claude Code, reaching 141 users at about $909 in API-priced tokens
Tabby (taewoo) · Claude Code
CaveatsSelf-reported, and the post is marked AI-assisted on DEV. Costs are estimates from token logs at Opus list prices, not what he paid. Part of the work counted was promo videos, not code. Small user numbers.
19 days since 5 Oct; v1.2 about a day from plan to release
Time
Solo developer builds ParkEase, a five-role parking marketplace with about 86,000 lines of TypeScript and 4,300+ tests, in five weeks with Claude Code
ParkEase (Onkar Deokate) · Claude Code
CaveatsSelf-reported by the builder. The post and the repo README differ on merged PRs (29 vs 32). ParkEase is live as a demo; no real users, bookings or revenue are reported. No AI cost is given in this post.
Five weeks (Sep 10 – Oct 13, 2026 per the repo)
Time
A CTO built a self-hosted family finance app in nine days with Codex and Claude Code, and has used it daily for two months
Keepard (Rodion, personal project) · OpenAI Codex, Claude Code
CaveatsSelf-reported by the builder, who says the numbers come from logs and git. Two users. He runs an agency and mentions a starter kit that grew out of the project. Code is open source at github.com/sars/keepard.
Nine calendar days, about 3 to 4 hours of attention a day
Build time
Repo fixer: a scheduled CircleCI pipeline with LLM fixers opens 150 migration PRs across an org overnight and keeps fixing new repos
Claire Alvis (Confident Commit) · repo fixer
CaveatsSelf-reported. The post does not name the employer, the LLM or coding agent used for fixes, or merge rates for the 150 PRs. The Claude skills are for managing the system, not necessarily for the fixes.
150 open PRs across the org by the next day
Migration PRs
Sparq builds a 22-agent internal platform with Claude Code: 34,000 lines across 453 commits
Sparq · Claude Code
CaveatsSparq is a consultancy and the post doubles as marketing for its AI readiness services. The authors say the numbers measure delivery volume from GitHub history, not business impact, and that there was no comparison build without Claude Code. Team size isn't stated.
~34,000 Python
Lines of code
Gemini 4 Argon runs unattended for 11 hours on the 205,000-line ADK Python codebase; 2 of its 6 optimizations ship
Google · Google Antigravity
CaveatsVendor launch post for its own model. Time to first model request in a new process stayed flat (3.07 s to 3.09 s). No cost figures.
~205,000 lines, ~800 source files, ~17,000 unit tests
Codebase
Claude Code ships 19 minor releases of the Smarter Django platform in 18 days, adding about 238,000 lines
Smarter · Claude Code
CaveatsSelf-reported by the project author, who notes lines of code are a poor productivity measure. Line counts come from GitHub contributor stats. The post covers data up to 17 October.
19 minor and 45 patch releases in 18 days
Releases
Solo developer ships Scumble, a desktop image editor in the Microsoft Store, five weeks after the first commit with Claude Code
Scumble (Dennis Schöneberg) · Claude Code
CaveatsSelf-reported by the developer. No cost figures. Line counts are approximate.
Five weeks from first commit to release 43
Time
Lucas Firmo's agent fleet moves a production iOS app to Swift 6 strict concurrency in 10 days, with zero warnings left
· Claude Code
CaveatsA short personal blog post. It doesn't name the app, team or employer, the codebase size, the number of agents, the cost, or which second model does the reviews. Claude Code is named only as the tool whose hooks enforce the rules.
10 days for the Swift 6 strict concurrency migration
Time
Juno merges 26 of its last 30 PostHog self-driving PRs, a roughly 90% merge rate, with the CEO still reviewing each one
Juno · PostHog self-driving, PostHog scout
CaveatsVendor-published PostHog customer story promoting PostHog self-driving, the product PostHog sells; the page has no author byline. Figures are self-reported by Juno CEO Marshall Gould. Roughly 90% and 26 of the last 30 describe a recent window, not a total volume, a time period, or a share of all Juno PRs. No calendar duration, cost or total merged-PR count is given. Gould still reads every PR, sometimes edits them, and often tests on a simulator; he has not turned on auto-merge. Some bugs cannot be reproduced easily because they depend on device state such as charging or low power mode. The page does not name the underlying coding model or a catalogue coding agent. "Fixed dozens of other issues" is PostHog's uncounted wording; the "Log all" medication-log example is described as Juno adding a feature after PostHog identified friction, without an explicit statement that self-driving authored that PR.
Roughly 90%
Self-driving PR merge rate
Mistral migrates 40,000 lines of a Fortran 77 reservoir simulator to C++ for a European energy operator, using a numerical parity harness and human-run agent workflows
Mistral AI (for an unnamed European energy operator) · Mistral Vibe
CaveatsVendor post about its own models and services; the customer is anonymous. It gives no total duration, cost, or count of PRs, and Vibe CLI is named only for the documentation step, not explicitly for the migration agents. Only the first 40,000 lines were done.
40,000 of 300,000 lines of Fortran 77 (first sprint, core functionality)
Lines migrated
Coinbase uses Claude Code to map its whole design system to Figma Code Connect in about four hours
Coinbase · Claude Code
CaveatsPublished by Figma about its own Code Connect product. The evaluation was three runs on one contrived design. Exact component count is given only as hundreds.
A few components to full design system in about 4 hours
Code Connect coverage
Solo builder ships SkillPilot, a paid product, with Claude Code in about three weeks, but 1,805 passing tests missed a dead checkout
SkillPilot (Carlos Infantes) · Claude Code
CaveatsSelf-reported by the builder. No revenue, user or exact token cost figures; the cost claim is relative to his previous tooling. Mostly a lessons post rather than an outcome report.
About three weeks
Build time
Industrial case study: Claude Code migrates 12 VB6 ERP features to C# .NET 10 at 70% equivalence for $50.29 in about an hour
Group Software (shopping-mall ERP) · Claude Code
CaveatsSingle-pass generation with no human refinement between iterations, so results understate iterative workflows. One VB6 ERP and one agent/model configuration. Only two high-complexity features.
12 (6 low, 4 medium, 2 high complexity)
Features migrated
Uber says agents are behind more than 70% of its pull requests, and explains how it cut cost per session 52% while usage grew 7x
Uber · Claude Code
CaveatsCompany writing about its own platform. 'Attributed to agents' isn't defined in the post. Mostly about cost and tooling rather than one delivered project. A related Pragmatic Engineer interview says the background agent Minion writes about 15% of production PRs, with a person reviewing every PR.
More than 70% of pull requests
Agent-attributed PRs
DoorDash's multi-agent system turns stale feature flags into merge-ready PRs for $4.79 and 14 minutes each
DoorDash · Claude
CaveatsSelf-reported by the team that built it, on 50 flags in Kotlin repositories. A human still confirms each target value and reviews the PR. Complex flags reached 85% (22/26) and outliers took about 40 minutes and $19.
45 of 50 stale flags
Usable PRs
Zalando's 2.5 years of agentic engineering across 250+ teams: a risk-based bot auto-approves 33% of PRs and cuts their lead time 20-40%
Zalando · GitHub Copilot, Claude Code, OpenCode
CaveatsWritten by Zalando's own engineering leadership. The 20-40% lead-time cut is for auto-approved PRs compared with all PRs. No productivity or cost totals; complexity findings come from four example codebases. Also mentions pi, a coding agent not in the site's tool list.
More than 250 engineering teams
Teams
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
DoorDash's in-house Flux cloud agent platform automates 130,000 engineering tasks in a month
DoorDash · Flux (DoorDash), Agent Gateway (DoorDash)
CaveatsPlatform post from the builders. Which coding agent harnesses Flux runs is not named. Counts are usage volumes; no merge rates, quality or time-saved figures are given.
130,000 in a single month
Engineering tasks automated
An agent-written 150,000-line Rust app shows refactoring one 17,155-line file cut input tokens per change by 83%
Giles Edwards-Alexander (writing on martinfowler.com) · Claude Code, Cursor
CaveatsOne app and one repeated change, measured by the builder. The author notes the dollar saving per change is small and the wider effect is unproven. Build time and total cost aren't given.
~150,000 lines (~120k Rust)
App size
Brex migrates 180 Kotlin microservices to Micronaut 4 in a month with one engineer and two self-hosted Cursor agents, after a manual attempt managed 50 in a quarter
Brex · Cursor
CaveatsBrex's own blog, written up as a Cursor success. A few automated PRs passed all tests and still caused subtle runtime bugs in production. No absolute dollar costs, model names or PR counts. Published July 2026, so older than this week's scan.
180 microservices in one month by one engineer
Services migrated
Wix's Code Migration Platform has a coding agent open migration PRs across hundreds of repos, saving 650 developer-days in a quarter
Wix · Code Migration Platform
CaveatsSelf-reported. The days-saved figure is calculated from services affected times estimated manual time per service, compared with actual time. The post does not name the coding agent or models, and says scripts handle a significant share of migrations without an LLM.
650 in a single quarter (their estimate)
Developer-days saved
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
iOS engineer builds Vibe Jam 2026 winner "A Game About Capybaras Delivering Food" in about 15 days with Claude Code: 188 commits, 27,000 lines, all code by AI
Capybara Delivery (Leo) · Claude Code
CaveatsSelf-reported by the builder. The game is a jam entry with about 5–10 minutes of gameplay and he does not plan to ship it on Steam. Art, 3D models, music and sound came from other AI tools (GPT Images, Grok, Tripo3D, Suno, ElevenLabs). His development cost breakdown is only in an image, so no cost is recorded here. Stack details beyond Three.js and a Cloudflare WebSocket for multiplayer are not given.
Around 15 days
Time
Solo staff engineer builds a 325,000-line workflow automation platform in 11 months of evenings and weekends with Claude Code
Flywheel (Travis Wilson) · Claude Code
CaveatsSelf-reported by the builder, who is promoting his product. The post says he is shipping to real users but gives no user or revenue numbers, and 1.0 had not shipped yet. Lines of code are a size measure, not an outcome. The year of the DEV post is not shown on the page; June 2026 is inferred from the post saying "Now (June 2026)".
325,000 lines of production code (170K Go, 145K TypeScript, 7.5K Python, 2,500 Terraform)
Codebase
Datadog migrates its live Stream Router from FoundationDB to PostgreSQL with Claude and Cursor; 45-minute operations now take ~1 second
Datadog · Claude, Cursor
CaveatsSelf-reported by the Datadog team that did the work. The AI tools were not autonomous: humans designed the schema, reviewed every generated skeleton, and wrote the optimised SQL (batching, UNNEST, CTEs), which the models then copied. Most of the performance and cost gains come from the new relational design, not from the AI tools; the post credits AI with making the implementation possible in the time frame. No count of methods, PRs or lines is given, and token spend is described only as significant.
~3 months (Dec 2025 – Feb 2026); proof of concept in 4 weeks
Design to production
A Mercari iOS engineer runs 22 Claude Code sessions in git worktrees to migrate screens to a new design system, opening about 140 PRs
Mercari (Mercoin client team) · Claude Code
CaveatsSelf-reported by one engineer. No figures on total time saved, defects or how long the migration would have taken by hand. The 'several months' span and PR count are approximate.
Around 140 over several months; up to 18 open at once
PRs
Forter migrates about 90% of 500 repos from Jenkins to GitHub Actions in under three months with a local Claude Code migration agent
Forter · Claude Code, GitHub Copilot
CaveatsCompany writing about its own work. Part 1 of a 3-part series; the three-month clock starts once the workflow was stable, not from the first attempt.
About 91% of 500, including 100% of non-custom repos
Repos migrated
Alfred Wegener Institute ports the FESOM2 ocean model (about 74,000 lines of Fortran) to C and then GPU-ready C++/Kokkos with Claude Code in a matter of weeks
Alfred Wegener Institute (FESOM2) · Claude Code
CaveatsWritten by the scientists who directed the port. The ported configuration covers the core ocean–sea-ice model (the full distribution is about 269,000 lines) and still lacks restart I/O, other vertical-coordinate variants and coupled-climate physics needed to replace the Fortran in production. Days with commits are not total effort, and no cost or human hours are given. An earlier attempt by the first author had failed. The output system was redesigned rather than ported.
73,991 lines in 109 files (core ocean–sea-ice configuration)
Fortran ported
Bloomberg's Pomona agent opens one tiny code-quality PR a day, and 32 of 39 were merged with a median close time of just over two hours
Bloomberg (with University College London) · Pomona
CaveatsIndustrial experience paper by Bloomberg engineers and UCL researchers about their own tool, one team, small sample. The paper says it cannot reveal which AI services or models were used, and data and code are not released.
39 over 55 workdays; 32 merged (82.1%)
PRs
Sixt's custom Claude agent migrates 780 iOS test files (~7,000 tests, 108,914 lines) from XCTest to Swift Testing for about $106
Sixt · Claude Agent SDK, Swift Testing migration agent (Sixt)
CaveatsWritten by the engineer who built the agent, on a personal Medium blog, with recruiting-style framing. Figures come from the agent's own cumulative stats. The author says the 21 failures were nearly all network errors to the LLM gateway, not migration mistakes. The manual-effort comparison ("months", 5–10 files a day per senior engineer) is the author's estimate. The migration is not fully completed or merged yet. Sixt used its internal LLM gateway; the post names the Anthropic SDK for bulk transforms and the Claude Agent SDK for the research and fixer agents.
780 across 50 modules
Files processed
Shopify's Slack-native agent River co-authors one in eight merged pull requests, with 3,536 merged in 30 days
Shopify · River (Shopify), Aquifer (Shopify)
CaveatsShopify's own engineering blog, co-authored by the agent itself; numbers come from River's own session table. It names no model or vendor, and gives no cost, review effort, or quality numbers for River's PRs. "Co-authored" doesn't say how much of each PR River wrote.
Shopify Engineering blog (Javier Moreno, co-authored by River)
"one in eight merged pull requests across Shopify is coauthored by it"
Share of merged PRs
Dropbox’s internal coding agent platform Nova accounts for roughly 1 in 12 pull requests, and runs flaky-test fixes and migrations
Dropbox · Nova, Deflaker
CaveatsWritten by Dropbox engineers. The 1 in 12 figure comes from the DX Annual write-up and has no date range or merge rate attached; the Nova introduction post gives no output numbers. Dropbox does not name the coding agents Nova runs today, only that it supports several; the earlier migrator was Goose-based.
Roughly 1 in 12 pull requests at Dropbox
Share of pull requests
Plaid’s Hamilton cloud coding agent writes thousands of PRs and accounts for about 20% of all merges
Plaid · Hamilton
CaveatsSelf-reported. Commercial coding harnesses are not named (tools left Unstated; Hamilton is internal). The 20% merge share and “thousands of PRs” lack absolute denominators. Sister adoption post is a secondary URL for company-wide context.
Roughly 20% of all merges
Hamilton share of merges
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
Google migrates production YouTube models from TensorFlow to JAX with a planner, orchestrator and coder agent system, 6.4x to 8x faster than by hand
Google (AI and Infrastructure) · Tool unstated
CaveatsGoogle writing about its own system; it also sells AI products. The post does not name the coding model or say how many models were migrated. Speedup is from their evaluations; a technical paper is referenced but not linked here.
6.4x to 8x over manual migration
Speedup
Sergio Azócar uses Claude Code to move a 1,670-file monorepo to oxlint and tsgo, cutting lint plus typecheck from 29s to 1.25s
Sergio Azócar · Claude Code
CaveatsPersonal blog. The speed-ups come from the new tools, not from Claude Code itself; the agent did the code changes. No time or cost figures for the monorepo migration itself.
~1,670 TypeScript files, 7 apps
Monorepo size
ZoomInfo rewrites a 938-file Angular feature to React in one week with a 15-agent Claude Code swarm, against a six-month 4–5 engineer baseline
ZoomInfo · Claude Code
CaveatsSelf-reported by ZoomInfo. The six-month figure is the historical cost to build the Angular feature, not a measured hand port of the same 938 files to React. No dollar cost or production defect counts. The post documents recurring AI slop (test memory leaks, architectural hallucinations, cyclical AST loops) that needed audit agents and human last-mile work.
938 files
Scope
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
Jmix migrates a CUBA Platform Timesheets app to Jmix with Codex in 25 hours against a 215-hour estimate
Jmix (Haulmont) · OpenAI Codex
CaveatsPublished by Jmix, which sells the target framework and the migration tooling, about its own sample application, so this is vendor-published. The baseline is Jmix's own Migration Advisor estimate, not a measured manual migration. Some behaviour was changed rather than reproduced (Ctrl+Enter instead of Enter for command input). The author says other projects may not see a similar reduction.
25 man-hours
Actual effort
Ten months of GitHub's Copilot coding agent in dotnet/runtime: 878 PRs, 535 merged, with a revert rate no worse than humans'
Microsoft (.NET team) · GitHub Copilot
CaveatsMicrosoft owns GitHub, so this is vendor-adjacent, though written by a .NET engineer with detailed data and caveats. CCA tasks were chosen by maintainers, so comparisons with human PRs are between different populations. Compute and CI costs are not analysed. Models named are those used at the time of one experiment.
878; 535 merged, 253 closed, 90 open (67.9% success)
CCA PRs in dotnet/runtime
Eve’s Slack-driven background agent WALL-E authors 22% of merge requests in its monorepo, 53% of them one-shot
Eve (Eve Legal) · OpenCode, WALL-E
CaveatsWritten by Eve’s own engineer. The post gives no absolute counts of merge requests, team size, cost or time period, and does not name the models used. One-shot means no human iteration before the merge request, as defined by Eve.
22% of all merge requests in the monorepo
Share of merge requests
Datadog has Claude Code and Codex build a Redis-compatible server and a Kafka-compatible streaming engine, and leans on test harnesses instead of code review
Datadog · Claude Code, OpenAI Codex, pup
CaveatsCompany writing about its own internal projects; redis-rust reached staging, not full production. First post in a series, so later results may differ. Datadog sells observability, which the approach leans on.
87% reduction after agent-guided optimisation (started at 8x Redis 8.4's memory)
redis-rust memory
W. David Betts builds SoundSignal, a full-stack building permit intelligence platform, in five days with Claude Code: 95 PRs, about 29,500 lines and 506 tests
SoundSignal (W. David Betts) · Claude Code
CaveatsSelf-reported by the builder. The developer worked full-time and says he knew what he wanted to build. He ran Claude Code with --dangerously-skip-permissions throughout and says he would not on a production codebase with secrets. The post does not report users or revenue. The cost is his estimate.
5 calendar days
Time
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
Instacart's Caper team migrates its smart-cart Android app to Jetpack Compose with AI, 5-7x faster on navigation
Instacart · Tool unstated
CaveatsNo coding tool or model is named. Speed-up and hours saved are estimates for Phase 2 only; Phase 3 was still in progress and Phase 4 had just started when published.
5-7x
Phase 2 speed-up
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
Dropbox indexes a 550,000-file monorepo in Cursor and accepts more than a million agent-generated lines a month
Dropbox · Cursor
CaveatsVendor-published Cursor customer story. Exact PR-throughput and cycle-time numbers are not given (only “upper tier of industry benchmarks”). Lines “accepted” are not the same as merged production code.
550,000+ files
Monorepo indexed
Cisco uses Codex across 15+ repos to cut build times ~20% and speed up C/C++ defect fixing
Cisco · OpenAI Codex
CaveatsVendor-published.
1,500+ per month
Engineering hours saved
Ramp's in-house background agent Inspect writes about 30% of merged PRs in its frontend and backend repos, without a mandate
Ramp · OpenCode, Inspect (built on OpenCode)
CaveatsCompany writing about its own tool. No figures for PR size, review effort, defects or cost. Says it supports all frontier models without naming which ones are used most.
About 30% of PRs merged to frontend and backend repos written by Inspect
Share of merged PRs
Google migrates 5,359 test files from JUnit3 to JUnit4 in 3 months with LLMs
Google · Google internal migration toolkit (fine-tuned Gemini)
CaveatsExperience report; Google uses its own model.
5,359
Files migrated
Altisource modernizes 350,000 lines of legacy Java with Amazon Q Developer
Altisource · Amazon Q Developer
CaveatsVendor-published. The 25% figure is described as 'up to' and for one modernization team; story points are a self-reported velocity measure.
350,000+ lines
Legacy Java modernized
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