quality_assurance · finance · workflow
Minions: Stripe's fully unattended one-shot coding agents merge over a thousand pull requests per week
Stripe's codebase — hundreds of millions of lines of code in a relatively uncommon Ruby/Sorbet stack with vast homegrown libraries — is far harder for LLM agents to navigate than a greenfield project, and developer attention is one of the company's most constrained resources.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Engineer invokes via Slack
Engineers kick off a minion by tagging the Slack app from the thread discussing a change, giving the minion access to the entire thread and any included links.
Tools used
ClaudeCursorgooseMCPSourcegraphToolshed
Outcome
Over a thousand pull requests are merged per week at Stripe that are completely minion-produced with no human-written code, enabling engineers to parallelize many tasks by spinning up multiple minions concurrently.
What failed first
Off-the-shelf LLM agents excel at greenfield prototyping but struggle with the scale, complexity, and maturity of Stripe's codebase, and no existing tool integrates with Stripe's unique developer-productivity infrastructure.
Results
Time savedover a thousand
Volumeover three million
Cost replacedwell over $1 trillion per year
Grounding & classification
Source type: technical build writeup
32 fields verified against source quotes.
agentic workflowai agentcode generationmulti agent workflowcode diff prknowledge basehuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedfinancial servicessoftwareemployee productivitythroughput increasetechnical build writeupquality assuranceagentic task executionai draft human approval