As coding agents write more and more code, the bottleneck shifts from producing code to understanding it. In his talk at the AI Engineer conference, Geoffrey Litt makes the case that the human’s job is not just to verify agent output, but to comprehend it deeply enough to participate in the creative loop.

He draws a sharp distinction between two postures:

  • Understand to verify — a binary thumbs-up/thumbs-down check, which agents are getting better and better at doing themselves
  • Understand to participate — building a rich enough mental model of the system to know what to evolve next, and to collaborate with the agent as an active creative partner

This connects directly to Margaret Storey and Simon Willison’s concept of cognitive debt: you can get away with not understanding what your agents built in the short term, but it compounds like tech debt and eventually bites you.

Litt shares three concrete techniques he uses daily:

  • Explanations first: before reading any diff, an agent-generated “explainer doc” teaches background context, states the goal, builds intuition, and walks through changes as prose — turning a pile of alphabetically-sorted files into a structured narrative
  • Quizzes as speed regulators: a five-question quiz at the bottom of each explainer, with a personal rule — “I won’t send code to others until I can pass the quiz.” This mechanically slows the AI loop to match the speed of human comprehension
  • Micro-worlds you inhabit: instead of reviewing a migration script he couldn’t follow, Litt asked Claude to build a “command center” video game — clicking through the port step-by-step, watching the old and new sites evolve side by side, building understanding by doing

The closing frame is the right one: the point of computing was always to augment, not just automate. Alan Kay’s 50-year-old vision — computers as dynamic simulations that help people think more clearly — is now more achievable than ever. As Litt puts it: “We don’t have to merely take ourselves out of the loop, we can get deeper in the loop too.”