The engineering loop

Watch an agent close the loop.

Running AI coding agents in production isn’t magic — it’s one primitive, repeated until the work is done: plan, act, observe, verify. Step through a real session and watch it happen.

A real session

One bug, one loop, stepped through

A payment test fails on CI but passes locally. Walk the agent through finding the root cause — not patching the symptom.

claude — ~/checkout-service

$ claude

> the payment test fails on CI but passes locally — find the real cause

>

planactobserveverifytheLOOP

plan

Plan

The agent reads the request and forms an approach before touching a single file. No fix yet — just intent.

step 1 / 7 · use ← → to step through

Four phases

The whole discipline, in one cycle

01 · plan

Read the request, form an approach. No edits yet — just intent and a hypothesis to test.

02 · act

Gather context and make a move: read files, search the codebase, run a command, apply an edit.

03 · observe

Look at what came back. Did the test pass? Did the error change? Update the hypothesis.

04 · verify

Prove it. Run the tests. Green closes the loop; red sends it back to plan with new evidence.

Make the agent reliable at this cycle — anticipate where it goes wrong and engineer the loop so it never does again — and you’re doing harness engineering. That’s the whole game.

This is what our courses teach

Learn to run this loop in production.

Read the free chapter