Stripe’s Payment Method Factory: Orchestrating agents for repeated, custom integrations

Stripe engineers cut payment integrations from up to six months to two to six weeks with more than 100 reusable prompts that improve after every run.

Stripe, the payments company, supports more than 125 payment methods, and each new integration could take six months because teams started from scratch. Engineers on the Local Payment Methods team built a "factory" of reusable prompts, each covering one step and one pull request. The factory has built three new integrations and moved ten existing ones to Stripe's newer systems.

• In a side-by-side test, one task took about 20 days of effort with a general coding agent and 4 days with the saved prompts.
• A second AI agent watches each run and notes where the working agent got lost, and an engineer uses those notes to improve the prompt.
• Each run saves the agents' learning notes, the decisions they made alone and the engineers' review comments, and an AI agent proposes prompt updates from them.
• An AI agent first coordinated the steps, but it was slow, costly and sometimes did the work itself, so the team moved coordination into ordinary code.

Saved prompts behave like shared code and need the same upkeep, fed by review comments; this is an inference. The piece is Stripe engineers' account of their own internal work.

Derived by Working Surface from the article; more in the Playbook. Source line: We learned that although an LLM can orchestrate a workflow, predictable coordination is better implemented in code.

3 October 2026: the written material that steers AI agents has become a maintained product that needs an owner, and setups without one decay into tangles that only the AI can navigate.