AI Skills with Matt Pocock
Gergely Orosz with Matt Pocock · 17 September 2026
Read the originalEngineer and educator Matt Pocock uses short instruction files that make AI coding agents question him closely about a plan, which leaves him more time for strategic work.
Matt Pocock is an engineer and educator who created the Total TypeScript course. On The Pragmatic Engineer podcast, host Gergely Orosz asked him how he plans and builds software with AI coding agents. Pocock relies on skills, short instruction files that an agent reads, and his best-known one tells the agent to "interview the user relentlessly".
- The skill, named "grill-me", is short. Pocock based it on an approach shared by Thariq Shihipar of Anthropic, in which an agent questions its user about a topic.
- Pocock borrows a distinction between tactical and strategic programming from John Ousterhout, author of A Philosophy of Software Design. He believes agents can do the tactical programming, which leaves engineers more time for strategic work.
- He asks agents to prove that their code works, and he is moving his coding sessions to cloud agents that keep running when his laptop is closed.
- This account comes from the episode's show notes and describes one engineer's practice.
A team can keep the questions it would ask about a plan in a file that the agent runs before any code is written. That use by a team is an inference and is not Pocock's claim.
Give the AI coding agent a short instruction file that makes it question the person requesting a build about the plan before any code is written.
Add the questions a design review would ask to the instructions an AI agent follows when planning, so that they are answered before anything is built.
Derived by Working Surface from the article. Source line: interview the user relentlessly
20 September 2026: the standing instructions people give AI agents, including what needs approval and what the agent must ask first.