Superpowers creator Jesse Vincent: managing AI agents is like managing junior engineers, 10x productivity
carsonfarmer · x · 2026-09-03
carsonfarmer highlights an AI Worth Using podcast interview with Jesse Vincent, creator of Superpowers (1.7M GitHub clones in two weeks), on six months of building with AI agents. Writing test rules in AGENTS.md feels more like system design than instruction-writing.
Key takeaways: falling test coverage is worse than failing tests; writing AI skills is straight-up people management (agents are smart, junior, tasteless, forgetful); agents execute better when told the why; Graphviz beats English for process clarity; strongly typed languages like Go and TypeScript yield more reliable agent code than Python; Vincent reports roughly 10x productivity, though taste and judgment remain irreducibly human.
More from coding & agent
- Fable 5.1 produced a result in ~10 minutes on the $100 plan — jasondeanlee · 2026-09-03
- 7 GitHub Repos Turn One AI Agent Into an OS: Memory, Model Routing, Free Compute Stacks — garrytan · 2026-09-03
- The Zvi: agents rewire your reflexes — annoyances now get fixed by just asking Claude Code — TheZvi · 2026-09-03
- "A smarter model in a bad system just makes expensive mistakes faster" — iamKierraD · 2026-09-03
- Omnara: open-source, self-hostable alternative to Claude managed agents — JaynitMakwana · 2026-09-03
- NanoCodana: open-source Claude Code-style coding agent that runs entirely in the browser — andrepimentaa7 · 2026-09-03