Loop/Prompt Library / Running AI agents well
🔁 Stop and check before continuing
After an agent finishes a task, it reports what is done and whether the next step is safe, then waits for you.
Use it when: You want agents to stop at the finish line instead of drifting into extra work.
🛑 Stops when: One task grade, one next-step grade, and one suggested action, with nothing started.
Copy this loop
Review [the task you just finished, or name it]. This is one check, not more work: do not start anything new. Say what changed, what you verified, what you did not touch, and what is uncertain. Grade the task: PASS, DELAY, or BLOCK. Separately grade the next step: GO, HOLD, CAP (with a clear limit), or BLOCK. Name exactly one allowed next action and anything off-limits. Then stop and wait for me, even if it is GO.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Idea from Forward Future's Loop Library · by Shinichi Nagata (@DecisionOS). Prompt rewritten in plain English by FixKit AI.
More loops like this
Agent workspace health check
Reads a project's notes and state, without changing anything, and grades whether a new agent could safely pick up the work.
Clean handoff note
Before a session ends, writes a note so the next person or agent can continue without guessing.
Predict, act, check
Before every meaningful action, the agent writes what it expects to happen, then checks if that is what really happened.
Lessons that stick
Keeps a playbook of lessons from repeated runs, tests one lesson at a time, and only keeps lessons that keep working.
Fair-test experiments
Improves a prompt or piece of code through saved, fairly compared experiments that can pick up again later.
Champion vs challenger
Keeps the current best prompt as champion, and a new version only replaces it if it wins on fresh test cases it never saw.