AI Skills with Matt Pocock

By Pragmatic Engineer

Categories: Product, Startup

Summary

Matt Pocock reveals how "leading words"—repeated phrases in AI prompts—can unlock emergent agent behavior and force deeper thinking; his Grill Me skill asked 35 questions for a simple API endpoint, demonstrating how AI can enforce software fundamentals that take 9 months to validate traditionally.

Key Takeaways

  1. Use 'leading words' (repeated phrases like 'tracer bullet') in AI prompts to guide agent behavior and make it mirror your thinking patterns back to you.
  2. The Grill Me skill asked 35 questions for one API endpoint, forcing exhaustive thinking upfront—a metric-driven approach to validate software fundamentals before 9-month mistakes compound.
  3. AI agents need context layers (specs, customer requests, history) to work effectively; Linear became 80% adopted in enterprise for this purpose as the ideal agent context provider.
  4. Software architecture fundamentals (monolith vs. microservices trade-offs) remain critical when working with AI agents—you can't hear what's wrong until mistakes surface months later.
  5. Pocock transitioned from 6 years as a voice coach to developer/educator, showing how non-traditional backgrounds inform teaching ability and emerge in AI skill design.

Related topics

Transcript Excerpt

It's annoying how damn it bro. >> Everyone's got a grill me story. It just has this weird emergent behavior where the models start thinking a little bit outside the box [music] and they start throwing ideas at you. >> I guess the idea of the tracer bullet is like a tracer bullet that leaves a mark. >> I just started using these phrases in my prompts [music] when I was talking to the agent and I started noticing that it was saying those phrases back to me. It was saying, "Okay, I'll turn this into a tracer bullet." This is what I call a leading word where you lead the agent just with a simple phrase that you repeat. How do I go about and find those fundamentals that matter and go back to? >> It's really tough because strategic programming has always been really hard to learn. I think of lea…

More from Pragmatic Engineer

Featured in