← back
"Software Fundamentals Matter More Than Ever" — Matt Pocock
Takeaway
AI coding works best when paired with classical software discipline — shared design concepts, ubiquitous language, and resistance to entropy.
Summary
- Matt Pocock argues specs-to-code/vibe coding produces increasingly bad code due to software entropy (Pragmatic Programmer); good fundamentals matter more, not less, with AI.
- Introduces a 'Grill Me' skill (~13k stars) that makes the AI interrogate the user 40-100 questions to reach a shared 'design concept' (Frederick Brooks) before producing a plan.
- Borrows Domain-Driven Design's ubiquitous language: maintain a markdown glossary of terminology so the AI thinks less verbosely and aligns implementation with intent.
- Frames Claude Code's default plan mode as too eager to create assets; recommends reaching shared understanding first.
ai-codingdesignclaude-code
Original description
AI coding tools are overhyped and powerful at the same time. Used well, they're extraordinary. Used badly, they'll bury you in spaghetti code faster than any human team could. The difference isn't the tool. It's the process. After 18 months of teaching developers to build with AI agents, Matt Pocock has watched the same patterns emerge: the devs who succeed aren't the ones who delegate everything or nothing. They're the ones who fall back on engineering fundamentals. In this talk, he shares the iterative process his students use to ship high-quality applications with AI agent swarms, and why the principles that make it work (ubiquitous language, vertical slices, TDD, deep modules) are decades-old ideas that didn't break. They got more important. Speaker info: - https://x.com/mattpocockuk - https://www.linkedin.com/in/mapocock/