Skip to content
Agents tracked: 501 Releases (7d): 777 Agent status: no reported issuesSince last limit reset: Claude 10d · Codex 8d For AI agents: Markdown Updated Nov 21, 2026
Case study StripeResults as reported by Stripe

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

  1. Engineers start a Minion from a Slack thread, a CLI, a web UI or internal tools (for example, a flaky-test ticket).
  2. Each run gets an isolated, pre-warmed devbox with no internet or production access.
  3. 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.
  4. Context comes through an internal MCP server, Toolshed, which has more than 400 tools.
  5. 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

  • As reported by Stripe: 'over a thousand pull requests merged each week' are produced entirely by Minions and reviewed by humans.

These figures are as reported by Stripe in Stripe engineering blog ↗ (Feb 9, 2026). AgentGid did not measure or independently verify them.

Takeaway. Give agents the same environments, linters and CI as your engineers, and cap the number of retry rounds.
AgentGid's take

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

Guides