Loop/Prompt Library / Loops from builders on X
🔁 Many speed-up ideas, one skeptical referee
A lead AI sends helpers off with one speed-up idea each, then re-measures every claimed win itself and keeps only real ones.
Use it when: Something is slow and you'd like many ideas tried overnight without trusting anyone's say-so.
🛑 Stops when: Only re-measured wins with identical results are kept. It stops when ideas run out or the limit is hit.
Copy this loop
Goal: make [program or step] faster. First, write a benchmark and record the starting time [5] times. Save a sample of the output to compare against. Then list up to [10] speed-up ideas, one per helper. Each helper tries only its idea in its own copy and reports its result. You are the referee: never trust a helper's number. Re-run the benchmark yourself, and keep a change only if it is faster in every run AND the output is exactly the same as before. Keep a table: idea, claimed gain, your measured gain, kept or rejected. Never merge to main. Stop when all ideas are tried, or after [8] hours. Show me the table and the combined change.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @aarondfrancis. 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.