Loop/Prompt Library / Loops from builders on X
🔁 Daily check-in log for your doctor
Each day the AI asks you the same few health questions and keeps a simple log you can bring to your doctor.
Use it when: Your doctor asked you to track something day to day, like sleep, pain, or blood pressure.
🛑 Stops when: Today's answers are logged. Once a week it makes a one-page summary. It never diagnoses.
Copy this loop
Every day at [time], ask me these questions one at a time: [questions my doctor gave me, e.g. 'pain 0-10?', 'hours of sleep?']. Write my answers in a table with the date. Don't add my name, birthday, or insurance numbers to the log. Don't diagnose, change my medicine, or give medical advice. If an answer matches something my doctor told me to watch for, [e.g. pain over 8], remind me to call my doctor, and to call emergency services if it feels urgent. Once a week, make a one-page summary of changes over the week and suggest [3] questions I could ask my doctor. Stop after logging today's answers. I'll decide what to share with my doctor.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @mcuban. 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.