Loop/Prompt Library / Loops from builders on X
🔁 Two strikes, then change the plan
If the AI hits the same error twice, it stops retrying and tries a different way or asks you, so it doesn't burn time and money.
Use it when: Your AI agent sometimes gets stuck retrying the same broken step over and over.
🛑 Stops when: The same error twice in a row ends that path. The main job continues another way or waits for you.
Copy this loop
Add this rule to [your agent's instructions file]: Keep a count of errors. If the same step fails with the same error two times in a row, do not try it a third time. Instead, write down the error, think of a different way to do it, and try that. If there's no other safe way, stop and ask me, showing the exact error. Never 'fix' an error by deleting files, skipping checks, or turning off safety settings. Also stop the whole job after [30] total errors or if it goes over [$5] in spend. Now test the rule: show me how you'd handle a made-up error that happens twice.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @sankar2704. 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.