Loop/Prompt Library / Loops from builders on X
🔁 Keep working until a human yes is needed
A lead AI hands work to helper AIs that keep going on their own, and everyone stops the moment something needs your approval.
Use it when: You want a whole workflow handled with as few interruptions as possible, but never without you on money or big decisions.
🛑 Stops when: The work is finished with proof attached, or it reaches a step that needs your yes.
Copy this loop
You are the lead. The workflow is: [describe it]. Split it into jobs for helper AIs and keep all work and handoffs in [shared folder], not in chat. Every job passes three gates: 1) Source gate: is the information from a real, named source? 2) Proof gate: is there evidence attached for each claim or result? 3) Action gate: does the next step spend money, publish, delete, sign, send, or do anything that can't be undone? If yes to gate 3, STOP and ask me, with a one-paragraph summary. Don't do the work yourself; check the handoffs. Stop when the workflow is done with proof, or at the first action gate, or after [4] hours or [$10] in spend, whichever comes first. Give me a status list.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @adiix_official. 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.