Loop/Prompt Library / Loops from builders on X
🔁 Check if you qualify for a settlement
Every so often the AI compares your purchases and accounts with current class-action settlements and tells you about possible matches.
Use it when: You suspect you're owed money from settlements but never check.
🛑 Stops when: Each run ends with a list of possible matches, or 'nothing new'.
Copy this loop
Every [month], look at the list of companies and products I've used, which I'll paste here: [list of companies, products, rough dates; no account or card numbers]. Check official settlement websites and trusted settlement news for current and upcoming class actions. For each possible match: settlement name, who qualifies, deadline, proof needed, the official claim website, and why you think I might qualify. Only list official claim sites; warn me about any site asking for payment or a bank login. Never send, post, buy, pay, delete, or sign anything; I do those myself. I'll file claims myself. Stop after the list, with at most [10] matches.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @sriramkri. 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.