Stripe Engineer Builds a T-Shirt Factory Factory to Benchmark Dev Tools for Agents
hazelcough · x · 2026-09-15
Stripe engineer Michelle Bu reflects on dogfooding in the agent era: five years ago it meant following a quickstart; today it means unblocking coding agents — completing 2FA, clicking through settings with no API, and coaxing Claude into using a live API key.
- She has long built unserious t-shirt shops (shirt.codes, emoji.fish, datetime.store) to understand her own APIs, since a real shop spans support, refunds, materials, shipping, and multiple state machines — a minimal testable unit of e-commerce.
- In 2026 the core question for dev tools becomes: how well do they work for users' agents, and are agents on the newest integration paths or decade-old Stack Overflow snippets from training data?
- Her answer: build a "factory factory" for t-shirt shops as an informal agent benchmark. 0 of 21 runs produced a t-shirt design she'd wear — an honest snapshot of where tools stand.
Related event: Stripe engineer tests 7 models building t-shirt stores: 7 of 21 runs usable(6 posts)→
More from coding & agent
- MiniCPM5-2B runs fully in-browser via WebGPU with agent tooling — victor · 2026-09-16
- Open-Source Agentic AI Security Lab: 9 Scenarios Breaking Agent Authorization — Rewanth_Tammana · 2026-09-16
- Models don't have agency, systems do: the one-token trick that seeds tool use — sethjuarez · 2026-09-16
- Agent Name Service Gives AI Agents Verifiable Identities via SCITT Receipts and OAuth — someone_somewhere_9 · 2026-09-16
- Dev ships multi-tenant MCP server for maginary, an OpenRouter-like multimedia generator — lutian · 2026-09-16
- Lessons from building agentic dev workflows: let software own the control loop — mostly_deterministic · 2026-09-16