Loop/Prompt Library / Loops from builders on X
🔁 Three AIs check your research
Splits research into three jobs: one AI finds where each claim came from, one checks what the sources really say, and one tries to poke holes. Only claims that survive are kept.
Use it when: You need an answer you can trust, and one AI alone sometimes makes things up.
🛑 Stops when: Every claim in the final answer survived all three checks, or the round limit is hit.
Copy this loop
Question: [question]. Step 1 (Scout): find where each key claim first came from, with links. Step 2 (Checker, a different AI if you can): read each source and say what it really proves, not what people say it proves. Step 3 (Critic, another AI): attack the draft answer and list weak spots. Fix the weak spots, then repeat steps 2 and 3, at most [3] rounds. Keep only claims that survive. Label each one: well supported, partly supported, or unknown. Stop when no new weak spots turn up, or after round 3. Show me the answer, the sources, and what was thrown out.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @SolSt1ne. 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.