
Jesse Vincent, creator of Superpowers (1.7M GitHub clones in two weeks), joins the show to share hard-won lessons from six months of building with AI agents. Jesse created RT (still running in Fortune 50 companies), led Perl 5, and built K-9 Mail (now Thunderbird for Android). He shares what happened when Claude started deleting his test suite, why managing AI agents mirrors managing junior engineers, and how persuasion principles from psychology transfer directly to prompt engineering. KEY TAKEAWAYS 00:00 Introduction 05:23 The only thing worse than a failing test is a reduction in test coverage — close every loophole 06:32 Writing AI skills is straight-up management; prose clarity and people skills matter more than syntax 07:39 Managing MIT undergrads in 2007 prepared Jesse for agents — smart, junior, no taste, poor memory 10:19 Skills need intent, not just process; agents execute better when they understand the why behind instructions 13:04 Encouragement outperforms pressure. Telling your agent you love it produces better outcomes faster and cheaper 19:11 Graphviz outperformed English for process clarity. Structured formats eliminate ambiguity that agents will otherwise misinterpret 26:58 Strongly typed languages like Go and TypeScript produce more reliable agent-written code than Python 30:19 Jesse is easily 10x more productive, but it's harder work; the typing was always the easy part 53:24 Taste and judgment remain irreducibly human. What makes your software worth building can't be automated See how people are actually working with AI at https://aiworthusing.com/builder-index RESOURCES MENTIONED Jesse Vincent LinkedIn https://www.linkedin.com/in/jessevincent/ Superpowers https://github.com/obra/superpowers Claude Code https://claude.com/product/claude-code Codex https://openai.com/codex/ Claude Goals https://code.claude.com/docs/en/goal Ghostty https://github.com/ghostty-org/ghostty TDD (Test-Driven Development) https://mridullpandey-superpowers.mintlify.app/skills/test-driven-development RT (Request Tracker) https://github.com/bestpractical/rt K-9 Mail https://k9mail.app/ Perl 5 https://github.com/Perl/perl5 Terminal-Bench https://www.tbench.ai/ Riemann Conjecture https://en.wikipedia.org/wiki/Riemann_hypothesis #AI #AgenticEngineering #Leadership
Podzilla Summary coming soon
Sign up to get notified when the full AI-powered summary is ready.
Free forever for up to 3 podcasts. No credit card required.

How a Dark Software Factory Actually Works with Justin McCarthy of Diffusion AI

Make Your AI Agents Compete with Harper Reed

Peter Steinberger: Stop Sending Me Code. Send Me Your Prompt

The Adversarial Review System Every AI Coding Agent Needs with Wes McKinney at Kenn Software
Free AI-powered recaps of AI Worth Using and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.