Loop/Prompt Library / Loops from builders on X
🔁 Get money back if the price drops after you buy
For 30 days after you buy something, the AI checks if the price dropped, and if so drafts a request for the difference.
Use it when: You often see things go on sale right after you buy them.
🛑 Stops when: 30 days pass, or you get the difference back.
Copy this loop
Here are my recent orders: [item, store, price paid, order date; no card numbers]. Find each store's price-adjustment policy (some refund the difference, some don't). Every day for [30] days, check the current price. If it drops below what I paid, tell me the new price, the difference, and whether the policy allows a refund. Draft a short, polite request I can send to support. If the store refuses, tell me whether returning and re-buying is allowed and worth it. Never send, post, buy, pay, delete, or sign anything; I do those myself. Stop when an item gets a refund or reaches day 30.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @blankspeaker. 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.