Loop/Prompt Library / Loops from builders on X
🔁 Keep going until a judge says 'simple enough'
For goals you can't test with a command, like 'simple enough' or 'clear enough', a separate AI judge decides when you're there.
Use it when: Your goal is a quality, not a number, like 'easy for a beginner to read'.
🛑 Stops when: The judge says the goal is met with reasons, or the round limit is hit.
Copy this loop
Goal: make [document, code, or design] [simple / clear / friendly] enough for [who it's for]. Make one improvement per round. After each round, a separate AI judge that didn't make the changes reads the result and answers: 'Is the goal met? yes/no. If no, what's the single biggest problem?' Fix that problem next round. Don't remove anything important just to make it shorter; the judge should check that too. Stop when the judge says yes, or after [8] rounds. Show me the before, the after, and the judge's final reasons.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @MatthewBerman. Prompt rewritten in plain English by FixKit AI.
More loops like this
One useful thing every night
You give the AI a short mission, and each night it picks one task that moves you closer and leaves it for you to check in the morning.
Two watchers keep your agent healthy
Two separate AI helpers read your main agent's logs, find what broke, and must both agree on a fix before it is used.
Weekly skill cleanup
Once a week, the AI grades every saved skill or saved prompt it uses, removes the dead ones, and merges the repeats.
Overnight drafts that learn from results
Each night the AI drafts tomorrow's post from your content plan, and reads your notes about what worked before it writes the next one.
Split the work, keep only what passes
Splits a big job across several AI helpers working side by side, checks each one's work, and keeps only the work that passes.
Practice a website task until it's reliable
The AI tries a website chore, learns from each failed try, and keeps adjusting until it has steps that work every time.