How Stripe's homegrown Minions agents turn Slack requests into merged PRs
Stripe built unattended coding agents, called Minions, on a fork of Block's goose agent. They take a task from Slack or an internal tool and return a CI-checked pull request for human review.
The problem
Stripe's codebase runs to hundreds of millions of lines, mostly Ruby with Sorbet and many in-house libraries that LLMs don't know. Developer attention was a scarce resource, and engineers wanted to run many small tasks in parallel.
How they did it
- Engineers start a Minion from a Slack thread, a CLI, a web UI or internal tools (for example, a flaky-test ticket).
- Each run gets an isolated, pre-warmed devbox with no internet or production access.
- The agent loop interleaves model steps with fixed steps for git, linters and tests, and reads the same rule files as Cursor and Claude Code.
- Context comes through an internal MCP server, Toolshed, which has more than 400 tools.
- Local lints run on each push, followed by at most two rounds of CI, before the PR is handed to a human reviewer.
Results
- As reported by Stripe: 'over a thousand pull requests merged each week' are produced entirely by Minions and reviewed by humans.
As reported by the source (Stripe engineering blog); AgentGid did not measure these figures.
This suits platform or infra teams with a mature CI, linter and sandbox setup, since the setup depends on isolated devboxes and an internal MCP server with 400+ tools, which most teams would need to build. The thousand-PRs-a-week figure is Stripe-reported, and human review effort scales with it. Goose is free (OSS) plus model costs; Pi, also Free (OSS), is a lighter alternative.
The agent used here
Similar use cases
Delegate a Linear issue to Codex and turn the result into a PR
With Codex installed in Linear, you can assign an issue to Codex or mention @Codex in a comment. It runs a cloud task on the linked repository and reports back in the issue.
Codex picks an environment and repository and starts a cloud task.
How Evinova drafted regulated GxP documentation and fixed bugs with Devin
Evinova, an AstraZeneca clinical-trial technology company, used Devin to draft GxP documents from Jira and source code and to run a scheduled bug-fixing playbook. Senior engineers…
As reported by Cognition: URS documents that took '35 to 40 hours' came out as first drafts 'at roughly 90% accuracy', a reported '8x faster GxP docu…
Porting JustHTML from Python to JavaScript with Codex CLI in an afternoon
Simon Willison gave Codex CLI a handful of high-level prompts to port JustHTML to a dependency-free JavaScript library. He published the repo and a playground.
The library passes 9,200 tests from the html5lib-tests suite.