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's Test: Only 7 of 21 AI Runs Built a Working T-Shirt Shop(7 posts)→
More from coding & agent
- One stale date silently broke a WhatsApp reply agent: 19 messages unanswered — petrusenko_max · 2026-11-02
- The 10X engineer is now just a SKILLS.md: 6 workflow rules for AI coding agents — mdancho84 · 2026-11-02
- Auditing my MCP credential broker: the worst hole was the config file — Relevant_Mousse_9117 · 2026-11-02
- AWS's open-source Strands Harness claims 45% cheaper than Claude Code, reigniting harness debate — blaizedsouza · 2026-11-02
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02
- Sketchy v0.1.6: AI diagrams use 29% fewer output tokens than plain text — Nkgsporty · 2026-11-02