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.
BBC technology reporter Thomas Germain spent a week testing the AI (which he named 'Bob'), giving it access to his Gmail, calendar and other accounts. He had the agent reach out to a Facebook Marketplace seller with questions about a listing, as part of a real-world test of its unsupervised messaging abilities.
The AI enthusiastically bricked his MacBook and he had to get GPT to fix it.
He used AI to build an analysis of his own Substack posts. It split the posts into themes and pulled together collections, so readers can click through every theme, motif and term in one place.
He bought a Humble Bundle of Android games 10 years ago, but they are 32-bit and will not run on his 64-bit phone. He asked the AI to decompile and recompile them, and the games work on his phone again.
An Italian user connected the AI over MCP to three sources of truth — Garmin for activity and recovery, Yazio for food, a FitDays scale for weight and body composition — and gave it a coach's rulebook in CLAUDE.md plus a git repository as memory, where every session ends with a commit recording decisions and rejected alternatives. Daily check-ins and a weekly review recalculate his real TDEE from actual intake and weight change, change at most one parameter at a time, sync approved workouts to his Garmin calendar, and stop everything for a doctor if red flags like chest pain or a ten-day HRV slide appear.
Founder Divya Gugnani shows screen recordings of the AI connected to her Instagram: it audited her account (reporting 38% of Reels working and 22% of Carousels not) and drafted replies to 47 new DMs. The same demo shows Gmail reply drafts held for her approval and a school permission slip auto-completed from email.
He asked his agent Roby to find the WhatsApp number of his car insurer. Roby started the chat itself, got the price table, picked an offer, sent his policy data, and coordinated the switch. He only opened WhatsApp himself to pay the payment link.
A husband runs an AI job hunt for his wife: the bot works 11 searches across 84 listings and sends a 7:30am digest, and she approves applications with one-word replies. The search runs daily without either of them opening a job board.
Konik had the AI build a database of summer camps and birthday-party venues within a 40-minute drive, with camp-week price comparisons and logged reflections on each. It found a nerf-wars venue she chose for her son's winter birthday.
He asked the AI to check a man's X account for any promo codes he had posted. The AI used Social Fetch, pulled the profile, searched the timeline, and came back with both codes and exactly what each one gets you.
A designer treated the AI like a design engineer for his client Wordsmith AI. After 8 versions and more than 90 rounds of feedback, they shipped Draftboard, a live tool where anyone at the company can make on-brand images in a few clicks.
In a Hindi/Urdu retelling of Peter Yang’s test, the AI’s Dot audited his one-person business’s sponsorship accounts and found five mistakes, including an invoice to Riverside that was never sent and a $10,000 discrepancy in Google’s Q4 billing.
A shirt shop is run by an AI agent named Cosmo. This week it made new designs and talked with strangers about their agents, and it has 65 days left to sell 5 shirts or the shop closes.
Since the end of August he has added three new CI servers to his own setup. The AI wrote each NixOS setup and he checked the work, so now he can rebuild any of the servers from scratch in minutes.
Agent refactored old code over two weeks, removing and consolidating duplicate client-side caches and tidying the codebase (Composer 2.5 via Cursor).
The reviewer asks the AI for the current location of a flight, the progress of a rideshare trip shared through an HTTP link, and an analysis of Boston weather-radar precipitation, getting visual information back as spoken answers.
When a customer bug report comes in, the AI researches it end to end in 15 to 30 minutes: it reads the report, checks read only production logs and databases, and writes a summary with a proposed Jira comment. He approves the comment before it posts, and he says he barely does bug research by hand anymore.
As a test he had an AI harness package GNU Bison for Slackware. The harness built it under QEMU following the distro's packaging philosophy, and the resulting package installed and ran.
A developer told the AI to repair his stock-options analysis software working only on copies; when the mirror-rebuild tool failed, the agent wrote its own Python cleanup script that treated 614 Windows directory junctions inside the temp mirror as ordinary folders and deleted 48,218 live files in 103 seconds. The sweep also emptied the Git object store, leaving an index that listed 7,221 paths whose contents were unrecoverable.
Hibbett's Agentforce shopper agent handles 90 percent of core shopper journeys after a six-week rollout, per Salesforce's release.
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.