The Loop Lab

Build the loop. Watch it run away. Engineer the stop.

"My students can chat with AI. I have no idea how to teach them to build one, and every 'AI literacy' kit I've seen is slides and vocabulary." If you run a CS classroom, a makerspace, a robotics team, or a hackathon, you know the gap: there is no hands-on curriculum for the one skill the field now rewards, building and governing autonomous agentic loops.

The Loop Lab is that curriculum. Across a tested sequence of buildable labs, your students assemble an agentic loop from scratch, deliberately watch it drift off-goal and burn tokens, then engineer the guardrails that make it trustworthy. Every lab hands you a runaway demo that lands every time and a drop-in grading rubric, so you teach the failure first and grade the judgment after, field-tested across classroom and hackathon sessions before it reached this page.

You will close the term with students who can build a loop, prove it works, make it stop, and explain when not to use one at all, the durable judgment no model upgrade erases. This is one of the first hands-on agent curricula written for the classroom, by a working learner-builder who teaches the way the field actually advances: ship, break, verify, repeat. Your lab plans for the next decade of AI, ready Monday morning.

Read chapter one free with Look Inside.

Part of the Build Agents You Can Trust series, in The Verifier's Library.