Stripe Details 'Minions' AI Coding Agents
What happened
Engineers at Stripe have detailed their work on internal AI agents called "Minions" that can autonomously handle end-to-end coding tasks. These agents can take a high-level prompt, such as "add a webhook for payment success," and then write, test, and deploy the necessary code. The project points toward a future of "agentic" development where AI can scaffold and maintain significant portions of a company's API layer.
Why it matters
- At Stripe, over 1,300 pull requests are merged each week that are entirely produced by Minions, with the code being reviewed by human engineers before deployment. - An engineer can initiate a Minion's task directly from a Slack thread; the agent then uses the conversation and any included links as its initial context for the coding problem. - The agents operate within isolated cloud developer environments called "devboxes," which are the same sandboxed environments used by Stripe's human engineers, preventing access to real user data or production systems. - The core of the Minion agent is a fork of "goose," an open-source coding agent originally developed by Block. - To gather context, Minions utilize a central server called "Toolshed" that hosts over 400 tools accessible via the Model Context Protocol (MCP), allowing them to query internal documentation, check build statuses, and more. - The workflow, managed by a system called "blueprints," interleaves deterministic code for required steps like running linters with flexible AI agent loops for creative problem-solving. - To prevent endless loops and control costs, a Minion is typically limited to a maximum of two attempts to fix continuous integration (CI) test failures before the task is returned to a human engineer. - Stripe's large and unique codebase, primarily written in Ruby with Sorbet typing rather than a more common framework like Rails, was a key motivation for building a custom, in-house agent.
Key numbers
- - At Stripe, over 1,300 pull requests are merged each week that are entirely produced by Minions, with the code being reviewed by human engineers before deployment.
- To gather context, Minions utilize a central server called "Toolshed" that hosts over 400 tools accessible via the Model Context Protocol (MCP), allowing them to query internal documentation, check build statuses, and more.
Quick answers
What happened in Stripe Details 'Minions' AI Coding Agents?
Engineers at Stripe have detailed their work on internal AI agents called "Minions" that can autonomously handle end-to-end coding tasks. These agents can take a high-level prompt, such as "add a webhook for payment success," and then write, test, and deploy the necessary code. The project points toward a future of "agentic" development where AI can scaffold and maintain significant portions of a company's API layer.
Why does Stripe Details 'Minions' AI Coding Agents matter?
At Stripe, over 1,300 pull requests are merged each week that are entirely produced by Minions, with the code being reviewed by human engineers before deployment. An engineer can initiate a Minion's task directly from a Slack thread; the agent then uses the conversation and any included links as its initial context for the coding problem. The agents operate within isolated cloud developer environments called "devboxes," which are the same sandboxed environments used by Stripe's human engineers, preventing access to real user data or production systems. The core of the Minion agent is a fork of "goose," an open-source coding agent originally developed by Block. To gather context, Minions utilize a central server called "Toolshed" that hosts over 400 tools accessible via the Model Context Protocol (MCP), allowing them to query internal documentation, check build statuses, and more. The workflow, managed by a system called "blueprints," interleaves deterministic code for required steps like running linters with flexible AI agent loops for creative problem-solving. To prevent endless loops and control costs, a Minion is typically limited to a maximum of two attempts to fix continuous integration (CI) test failures before the task is returned to a human engineer. Stripe's large and unique codebase, primarily written in Ruby with Sorbet typing rather than a more common framework like Rails, was a key motivation for building a custom, in-house agent.
