Loop/Prompt Library / Running AI agents well
🔁 Lessons that stick
Keeps a playbook of lessons from repeated runs, tests one lesson at a time, and only keeps lessons that keep working.
Use it when: The same task runs over and over and you want real lessons to carry forward.
🛑 Stops when: Every kept lesson has worked across several separate runs. Lessons that stop helping are removed.
Copy this loop
Keep a versioned playbook of lessons for [task] in [folder, e.g. playbook/]. Treat each lesson as a suggestion, not a rule. At the start of each run, pick at most one lesson to test. Measure the result with the task's own success check and log it. Promote a lesson only after it works in [3] separate runs; never from one lucky win. Remove lessons that stop helping. The playbook can never authorize production, money, privacy, or deletion actions. Finish each run with the playbook changes.
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 AKT (@akt199009). 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.
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.
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.
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.