AI Summary
5 min readMatt Pocock, creator of Total TypeScript and the most-starred AI skills repository on GitHub, did not start his career in tech. For six years he was a voice coach and singing teacher in London, a background that gave him an unusual advantage when he later taught himself to code: he could explain technical concepts clearly to other people. That teaching instinct eventually led him to create Total TypeScript, a course that hit seven figures in revenue within months of launching. But when AI arrived, Pocock faced the same question many educators are confronting: what happens when knowledge becomes cheap to acquire?
The answer, he argues, is that the fundamentals of software engineering have not become obsolete. They have become more important.
The two layers of programming
Pocock draws a distinction between tactical programming and strategic programming. Tactical programming is the syntax, the implementation details, the "what"—the kind of work an LLM can now handle easily. Strategic programming is the "why": the long-term thinking about architecture, trade-offs, and maintainability. AI has largely eaten the tactical layer, he says, and the strategic layer is where human judgment becomes the bottleneck.
Continue reading the full summary in the app — free to try.
Read Full Summary →Free • No credit card required
Never miss an episode of The Pragmatic Engineer
Get every new episode summarized in your inbox — free, ~5 minutes to read.
No spam. Unsubscribe anytime.
What you'll learn
- 1 (00:04) **Matt Pocock’s Grilling Skill** - Matt describes the intense, question-heavy nature of his "Grill Me" skill, which he created to force deeper thinking.
- 2 (02:32) **From Voice Coach to Developer** - Matt shares his unusual career path, starting as a voice coach and singing teacher for six years before becoming a self-taught developer.
- 3 (05:48) **Early Career and TypeScript Adoption** - Matt describes his early jobs at agencies and how he championed TypeScript to solve a major bottleneck.
- 4 (08:16) **Open Source and the XState Company** - Matt explains how his work on making the XState state machine library type-safe led to a job at the company founded by David Khourshid.
- 5 (11:37) **The Birth of Total TypeScript** - Matt recounts how he started creating two-minute TypeScript tips on Twitter, which went viral and led to the creation of his highly successful course.
- 6 (22:25) **AI's Impact on Education** - Matt discusses how AI has fundamentally changed the value of knowledge, forcing him to pivot his educational focus.
- 7 (24:59) **The Pivot to Strategic Programming** - After a "winter break" where AI models became dramatically better, Matt realized agents could handle the "tactical" coding, leaving humans to focus on strategy.
+ Full timestamped outline available in the app
Guests on this episode
Show Notes
Brought to You By:
• turbopuffer – a vector and full-text search engine built on object storage. It’s fast, cheap, and extremely scalable
• Linear – the product development system for teams and agents
• WorkOS – everything you need to make your app enterprise ready.
—
Why is the “grill-me” skill so popular, and why does its creator swear by the importance of software fundamentals? Matt Pocock created this widely-used skill – and many others – alongside being an educator, content creator, and engineer. His latest course is AI Hero, and he previously created the Total TypeScript course that generated more than $2.5 million in sales.
In this episode, Matt and I discuss his unconventional path from working as a voice teacher to becoming a developer and going all-in on technical education. He reveals how communication skills helped him break into tech, why he took an unusual three-days-a-week contract at Vercel, and how he built Total TypeScript through workshops, courses, and a lot of free content.
We also explore “strategic coding,” and how he uses skills like “grill me” and “wayfinder” to plan, delegate, and course-correct with AI agents. Matt explains his “day shift” and “night shift” approach, why splitting context up can keep agents in their “smart zone,” and how concepts from classic software engineering books can guide agents to do better. In this episode, there’s also local versus cloud workflows, whether agents need TDD, how AI is changing the ways that engineers learn the fundamentals, and why humans are still essential in teaching.
Timestamps
00:00 Intro
05:48 How Matt got into tech
10:14 How Matt got into open source
12:58 Joining Vercel
18:39 Total TypeScript
23:21 AI’s impact on technical education
30:32 Building reusable skills for AI coding agents
40:46 The “smart zone” vs the “dumb zone”
45:02 The wayfinder skill
47:52 Why agents excel at software engineering
50:54 “Leading words”
1:01:10 Learning the fundamentals
1:09:17 Local vs. cloud agents
1:12:36 Planning vs. course-correcting
1:18:13 TDD and agents
1:23:06 Living in the UK
1:24:21 Teaching: the human part
1:28:36 Advice for junior engineers
1:31:07 Gardeners and great engineers
1:34:01 Book recommendation
—
The Pragmatic Engineer de
More from this podcast
The Pragmatic Engineer →