Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
Laura Legge (32K followers) challenged herself to feed a family of four on $30/week using pantry items (salmon, frozen mixed veggies, turkey breast, oils, seasonings). The 'the AI Atlas' app returned a seven-dinner plan with recipes, a missing-items grocery list, and a browser price comparison across Walmart, Stater Bros., and ALDI for zip code 92880 — Walmart won at $29.66.
Last spring he gave an agent an API key with no cap on it. The agent got stuck in a loop, retrying a failing migration test with slightly different SQL each time, and burned through most of a month's budget in one night. Nothing malicious, just a loop with no exit. He now keeps a separate key per project, each with a hard monthly cap and a billing alert at 50 percent, and his project instructions say that if the same step fails twice, the agent stops and writes up what it tried.
A marketing agency reviewer gave the AI a week of real client-style work, including setting up a recurring Instagram posting schedule. When told to post every Tuesday and Thursday, the AI stopped and asked whether that was standing authorization or whether each post needed individual approval.
The AI watches Poshmark and Vinted every two hours for authentic vintage Olga nightgowns, negotiates with sellers and buys on the user's approval, landing pieces at $20, $50 and $65.
The solo maintainer of the karasu modeling language runs dependency updates through an AI skill that investigates each Dependabot PR before anyone merges: release notes, the diff between tags, publisher or ownership changes, install-time scripts, lockfile edges and known advisories, written up as merge, hold or reject recommendations in a design doc. In the week of Oct 10–17 three triage rounds fed 88 merged PRs (16 from Dependabot) and 12 architecture decision records, and the process caught a rebuilt lockfile silently moving a package off the reviewed version.
He connected the AI to iMessage on his Mac with a BlueBubbles server, polling about every 5 seconds and waking only for allowlisted senders and chats. When he moved dinner with his wife by 30 minutes in his calendar, the AI messaged the family chat on its own and told his wife about the change.
Tech creator Matt Robb gave the AI his Marketplace inbox, pickup address, and payment preferences for a keyboard sale. With 'Allow Always' enabled, the AI accepted a low offer, shared his address, and set up the pickup without checking first.
He had the AI collect his will and trust documents and check them against state statutes. The review found missing signatures, an illegal clause, and outdated law references, and he fired his attorney the same day.
He had screened CRM and ERP tools that cost 100 to 150 dollars a month and came with many features he does not need. His friend built exactly what he needs with AI instead.
He wanted to see if AI could build a real production website end to end without him writing any code. The AI wrote all of the new Umbraco Kent Meetup site, built headless on Umbraco 17 and Astro and hosted on Azure for less than a Cloud starter plan.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.