Stripe Engineer's New Substack: Can Models Build Fully Functioning T-Shirt Shops? Sort Of
hazelcough · x · 2026-09-15
Stripe's Michelle Bu launched the Substack "Breaking Change!" to document what she learns while building through the biggest breaking change to how we work, at Stripe and beyond.
The first post, "Building a t-shirt factory factory," treats a t-shirt shop as a useful minimal testable unit of e-commerce: real shops handle cost of goods, the full order lifecycle, support and refunds, and orchestrate multiple state machines across first- and third-party systems. Her premise: in 2026 no one follows a website quickstart anymore, so the real questions are how well developer tools work for users' agents, and whether those agents use the newest integration paths or are stuck on decade-old Stack Overflow snippets in their training data.
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