"Software Fundamentals Matter More Than Ever"
summary
Eighteen months of classroom experience yields an iterative process for shipping apps with AI agent swarms: a Grill Me prompt that forces up to 100 clarifying questions, a code scanner that generates a ubiquitous language markdown, enforced TDD to make the LLM take small steps, and refactoring into deep modules so tests target simple interfaces. A GitHub repo (macpocockskills) and aihero.dev host the skills; one skill gets ~13,000 stars, showing these concrete tools actually change outcomes.
AI-written summary · about
chapters (11)
- 0:00Software fundamentals
- 1:12Specs-to-code fails
- 4:20AI didn’t do what I wanted
- 7:10Align AI with goals
- 9:38Shared language with AI
- 10:00AI-generated code flaws
- 11:24TDD for AI development
- 14:10Deep modules for testability
- 15:12Preventing AI fatigue
- 16:35Daily system design
- 17:37AI as programmer
related talks
56mFundamentals of Software Engineering In the age of AI
01h 02mSkills for the age of AI developer tools
51mCode Smarter, Not Harder: AI-Powered Dev Hacks for All
45mThe AI Revolution in Software Development: From Code Writing to Quality Assurance
54mKeynote: AI-Powered App Development
16m5 most useful AI skills that I use with Flutter everyday
32mBeyond the Hype: A Pragmatic Look at How Developers Actually Use AI Tools
26mThe Developer's Roadmap for the wave of AI Powered Applications