Background agents on in-house infrastructure: 26 sourced coding agent stories
Agents run in cloud sandboxes or on internal platforms, triggered from tickets, Slack, CI or schedules rather than a developer's laptop. This technique sits in the Doing the work stage. Of the 26 stories, 4 were published by a tool vendor and 22 by the people who did the work. 21 involve an existing codebase and 2 started from scratch. Every number links to where it was published.
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
DANA Indonesia cut a design-system component migration from 24 hours to 52 minutes per batch with Cursor agents run from Notion
DANA Indonesia · Cursor
CaveatsVendor customer story from Notion, which sells the External Agent feature. Counts PRs reaching review, not merged; no figures for review time, rework or defects. The page says most customers use iPhones while the migration is the Android app.
52 minutes, down from an average of 24 hours
Time from assignment to review-ready PR per batch
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
Uber's AutoClean agents remove stale feature flags across its monorepos, with over 16,000 flags and 1,000,000 lines cleaned
Uber · AutoClean (Uber), PolyglotPiranha (Uber, open source), CodeCourt (Uber)
CaveatsUber's own engineering blog about its in-house system, so self-reported, though Uber doesn't sell the tool. The 16,000 flags and 1,000,000 lines are totals "over the past few years" and the post doesn't say how many came from the agentic version versus earlier PolyglotPiranha-based automation. It names no AI model or vendor, and gives no cost, time per cleanup, acceptance or abandonment rates, or count of diffs rejected by reviewers.
"more than 16,000 flags" ("Over the past few years")
Flags cleaned
Navan moves 8 apps and 15 libraries to Spring Boot 4 in about a week with Cursor cloud agents, against over a month for a comparable migration two years earlier
Navan · Cursor
CaveatsVendor customer story with a sales pitch at the end. The month-long baseline is one earlier migration, not a controlled comparison. No figures on review effort, defects or rollbacks.
About a week for 8 apps and 15 libraries (previous comparable migration: over a month)
Migration time
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
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
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
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
Vercel's AI SDK software factory authors 25–35% of merged PRs and closes most issues, four weeks into production
Vercel · ai-sdk-factory (Vercel)
CaveatsSelf-reported by Vercel, which sells the Sandbox, Functions, Queues and Blob products the factory runs on and promotes a one-click deployable version, so this is vendor-published. The post does not name which coding agent or model powers the factory's agents (it mentions Opus 4.6 only as the trigger for the PR surge), so the tool is Unstated. Results cover just over four weeks. The intro says the factory closes 70-80% of issues while the results section says over 75% of closed issues in July; these are shares of closed issues, not of all open issues. No absolute PR counts are given. The open-issue drop is not attributed solely to the factory.
25–35%
Share of weekly merged PRs authored by the factory
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
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
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
Stripe builds continuous Java upgrades with Minions fixing CI failures, reaching 93%+ of services on JDK 17 within a week of rollout
Stripe · AutoJDK, Minions
CaveatsMuch of the work is deterministic build-graph automation; agents handle a subset of failures. The post doesn't say how many fixes came from Minions or which model they use.
93%+ of services within under a week of rollout
JDK 17 adoption
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
Spotify's Honk agent rolls out 240 dataset migration PRs across downstream pipelines, saving an estimated 10 engineering weeks
Spotify · Claude, Honk, Backstage, Fleetshift
CaveatsCompany writing about its own platform. Scio pipelines weren't migrated by the agent, and without tests in most repos the agent couldn't verify its changes. The post doesn't say how many of the 240 PRs merged. Publish date read from page metadata.
240
Automated PRs
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
Stripe's unattended Minions agents produce over 1,300 merged pull requests a week, human-reviewed but with no human-written code
Stripe · Goose, Minions, Devbox, Blueprints
CaveatsSelf-reported. No merge rate, revert rate or time-saved figures. Weekly PR counts lack a denominator of total Stripe PRs. Goose is a Stripe-internal fork; Cursor and Claude Code are used separately by engineers and are not part of Minions.
Over 1,300 a week, completely minion-produced (up from 1,000 at Part 1)
Merged PRs
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
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
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
Spotify's background coding agent merges 1,500+ migration PRs with 60–90% time savings
Spotify · Claude Code, Claude Agent SDK, Honk (Spotify)
CaveatsSelf-reported, and the time-saving method isn't detailed. Spotify flags slow and unpredictable agent runs, the need for new validation, safety guardrails and significant LLM cost. Later posts say prompts still evolve 'mostly by intuition'. A June 2026 Spotify post reports 76% more PRs to review, so review has become the bottleneck. Anthropic also publishes a co-marketing case study that claims 'up to 90%'.
1,500+
Agent PRs merged to production
Puzzmo’s Orta Therox clears years of tech-debt migrations in six weeks with Claude Code and ships Missing Link from a prototype monorepo
Puzzmo (Orta Therox) · Claude Code
CaveatsSelf-reported retrospective. Author notes PR/commit/LOC charts did not jump despite felt pace increase, and cites research that developers overestimate AI impact. No per-migration timings, costs, or defect counts. Missing Link is described as an experiment that created product-process tension about keeping prototype code in production.
6 weeks of Claude Code use
Window