Loop/Prompt Library / Loops from builders on X
🔁 Make companies compete for your money
The AI collects real quotes for something you need, then uses the best one to ask the others to beat it, until the price stops dropping.
Use it when: You need a service or big purchase (movers, insurance, a contractor) and want the best fair price.
🛑 Stops when: No one beats the best offer, or after [3] rounds. You pick and pay yourself.
Copy this loop
I need: [what, where, when, any must-haves]. Find [5] well-reviewed providers. Draft a short request-for-quote message for each; show them to me before anything is sent. When quotes come back, put them in a table: price, total fees, what's included, reviews, and anything missing. Then draft a polite message to each provider sharing the best total price and asking if they can beat it. I send every message myself. Repeat at most [3] rounds. Never share my account numbers, ID numbers, or payment details. Stop when no one beats the best offer, or after round 3. Recommend one, with reasons, and list questions I should ask before I sign.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @liam_fallen. 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.