Loop/Prompt Library / Loops from builders on X
🔁 Morning trend scout, you pick the topic
Each morning the AI compares today's chatter with the past week and month and brings back at most three checked ideas. Nothing gets written until you choose.
Use it when: You make content and want ideas based on what's actually rising, not random guesses.
🛑 Stops when: Up to three ideas are delivered each morning. Writing starts only after you approve one.
Copy this loop
Every morning at [time], look at [sources, e.g. two forums and one social site] for [my topic]. Compare the last 24 hours with the last 7 days and the last 28 days. Find topics that are clearly rising, not just loud today. Bring me at most [3] ideas, or fewer if nothing stands out. For each: one-line summary, why now (with numbers), and 2 source links you checked. Don't write a draft yet. Wait for me to pick one. After I pick, list the sources and any images you'd use, and wait for my OK again before drafting. Never send, post, buy, pay, delete, or sign anything; I do those myself. Stop after delivering today's ideas, or after [20] minutes.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @0xGenAi. 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.