Loop/Prompt Library / Loops from builders on X
🔁 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.
Use it when: You have a big, repetitive job (like updating many files) that can be split into pieces that don't touch each other.
🛑 Stops when: Every piece has passed its check and been kept, or failed twice and been set aside for you.
Copy this loop
Here is the big job: [job]. First, write a plan as a list of small pieces that don't touch the same files, and a check for each piece (for example: tests pass, file builds). Show me the plan and wait for my OK. Then give each piece to a separate helper working in its own copy of the project. When a helper finishes, run its check. If it passes, keep it. If it fails, let that helper try [1] more time, then set it aside. Never let a helper change the checks. Use at most [number] helpers and [budget or time] total. Stop when every piece is kept or set aside. Show me one combined list of changes, plus the pieces that failed and why.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @TheAhmadOsman. 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.
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.
Make the AI run your checks
Writes down the checks you normally do by hand, so the AI runs them after every change and must fix any failure before it moves on.