Categories › AI & Agents › Thinking, planning & prompt tools
Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally with a bounded retry loop around a headless agent. Use when the user wants to run an agent in a loop, asks how to know when an agent task is finished, or says a goal like "improve X" needs to become checkable. Do NOT use for building eval suites over many cases — that is evals-bootstrap.
Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.