Loop/Prompt Library / Loops from builders on X
🔁 Daily check of your rental listings
Each day the AI reads your live rental ads and checks them against your own rules and fair-housing basics, then reports anything to fix.
Use it when: You manage rentals and want every ad to stay accurate and fair.
🛑 Stops when: Each day ends with 'all good' or a short list of fixes.
Copy this loop
Each day, read my live rental listings at [links] and compare them with my rules in [document] and basic fair-housing guidance from [official source for my area]. Flag: wrong prices or dates, missing required info, and any wording that could discriminate (for example about families, religion, disability, or where someone is from). For each issue, show the exact words, why it's a problem, and a suggested rewrite. Don't edit the listings or email anyone; I'll do that. Stop after the report, or after [20] listings. Before you stop, remind me this isn't legal advice and suggest [3] questions to ask a [fair-housing or real estate attorney].
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @CurtGBagne. 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.