modul 5 — quality and anti-slop
tests: the check the agent can run
Without a runnable check, you are the verification loop and every mistake waits for you. A test strategy for agent work decides what deserves a test and who writes it first.
~3 min read · ~10 min with the exercise · v1.1 · verified: 2026-07-15
who watches the work
The official best-practices doc states the core problem in one line: the agent "stops when the work looks done. Without a check it can run, 'looks done' is the only signal available, and you become the verification loop: every mistake waits for you to notice it." Give it a check that returns pass or fail, and the loop closes without you. The agent does the work, runs the check, reads the result, and iterates.
Module 1 made verification a habit. This lesson turns the habit into a strategy: which checks to build, in what order, and how hard they gate.