Loop/Prompt Library / Loops from builders on X
🔁 Build a notes vault from your connected apps
Goes through each app you've connected, one at a time, and writes what matters into tidy, linked notes.
Use it when: Your important info is spread across email, docs, and calendars and you want one organized notebook.
🛑 Stops when: Every connected app has been covered once, or the time limit is hit.
Copy this loop
Build a notes vault in [folder] from these connected apps: [list]. Go one app at a time. For each, write notes on projects, people you work with (work role only), decisions, and dates that matter, with a link back to where you found each one. Link related notes together. Never copy passwords, account numbers, ID numbers, or health details; skip them. Read only; don't send, change, or delete anything in the apps. After each app, update [INDEX.md] with what you covered. Stop when every app is done, or after [6] hours of work. Then show me the index and anything you weren't sure about.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @nickvasilescu. 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.