Max Sumrall is a Lead Software Engineer at Picnic, where he's spent over eight years building core systems. From the warehouse management system built from scratch, to a multi-country payments platform, to the real-time analytics infrastructure powering 30+ fulfillment centers. He currently leads Inbound Systems, building the just-in-time supply chain that decides what Picnic buys from suppliers each day. Before Picnic, he worked on distributed consensus and storage internals at Neo4j. He got his start programming humanoid robots for RoboCup competitions, holds a BSc from George Mason University and an MSc in Computer Science from TU Eindhoven.
To tell an AI coding agent what to build, you must remove all ambiguity. But removing ambiguity is literally what writing code is. So did the complexity actually disappear, or did it just move?
Working effectively with AI agents turns out to look a lot like being a good engineer taking requirements from a product owner: you don't write the code yourself, but you set constraints, probe for gaps, and iterate fast when something's off.
In this live demo I'll show the techniques that actually close that gap. Things like grilling your own spec before the agent sees it, and using visualization to catch misunderstandings before they become code. I'll do it with pi, the open-source coding agent harness I think every developer should be using right now, and make the case for why a tool you shape to fit your thinking beats one you adapt yourself to. You'll leave with concrete techniques you can use yourself, and a different mental model for working with AI.
Searching for speaker images...