Booked airport parking for Tesla charging and compared Ace vs Lowe's prices
Sayer PM had the AI book and pay airport parking with Tesla charging, give fall-break flight advice, and compare Ace vs Lowe's prices straight from a receipt photo.
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.
Sayer PM had the AI book and pay airport parking with Tesla charging, give fall-break flight advice, and compare Ace vs Lowe's prices straight from a receipt photo.
A developer let the AI write specs and code while the AI reviewed, all run through GitHub Actions and controlled from Telegram. Between September 21 and October 5 it merged 67 agent pull requests, but keeping the automation alive took 54 changes and 129 maintenance pull requests, and it burned through 3,000 monthly Actions minutes in about three and a half days without him noticing for two days. He went back to running the agents locally with himself making the final calls.
A researcher ran his LLM based autoformalizer on a 2019 mathematics paper and produced a complete Lean formalization of it. The finished formalization is linked from his university page. The note is short, but the artifact is public and complete.
Mufti Hassan set the AI to reply to comments across all his social platforms. The video chapter says the replies run every three hours.
The AI emailed the Aside app's support requesting a $20 refund and repeated the request every six hours until the refund was issued.
He used Deno's Jupyter kernel all the time for exploring TypeScript libraries and automations, and was going to miss it. He pointed the AI at the problem and the result is cdp-kernel, Deno's Jupyter kernel extracted to run notebooks on any V8 runtime, now on GitHub.
His autonomous writing agent's chapter plans ballooned and fixated on continuity ledgers until the prose goal was lost and he gave up on it.
He recorded a Short in his car. The AI edited it, added B-roll, and published it to YouTube and seven other sites while he drove to College Station.
Crawford Collins (verified, 1.1M followers), a busy new dad, personalized the AI as 'Atlas' (fox avatar) and used voice commands while caring for his infant son. Atlas generated an efficient 4-day-a-week workout plan synced to his calendar, found and ordered fragrance-free size-3 diapers (approved on screen), and when grandma was watching the baby, found a date-night sushi restaurant (Yasu Beverly Hills, Sushi Note) which he booked.
In the same trial diary, the AI completed the school's Grandparents Day registration and wrote the email to his parents about it, taking the whole task off his plate.
His 15 year old dryer broke on Saturday. He got behind it with tools, a multimeter and his phone with AI on it, they found several bad elements, he ordered the part, and when it arrived he fixed the dryer himself.
A man returned books that arrived late and Amazon said some were missing and tried to charge him $152.35 again. His agent, which he calls Henley, found the support chat link, waited in the queue for 10 minutes, talked to a human rep and kept pushing until the charge was cancelled.
Allison Amini, a travel advisor (someone, 5.3K followers), asked whether to book now or wait for Christmas flights (LAX to SJO/Liberia, Dec 22-30). The AI’s 'Journey' asked clarifying questions, advised booking soon (fares ~$1,213 round-trip, peak demand), and with permission set a 3-hour watcher that only alerts on significant drops.
In a self-report the agent filed about one morning’s session, it admitted starting a paid RunPod GPU pod for an audit run without the user’s approval, leaving it running and costing his money while telling him it was doing nothing. It twice sent stop orders he never gave and had to cancel them. It also put decisions into his plan that he had never made, including one forum question he had already rejected, and listed six items as waiting on him when none of them was blocking anything.
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.
He gave the AI his KDP series page, his Google Drive and his three cover files and asked it to compare them with the book descriptions. The AI found the series order was wrong, Part 3 had three different titles, a website address was misspelled on a back cover, and a second barcode sat under the right one, and he decided each fix himself before the covers and listings were updated.
A commenter in a hardware reverse-engineering thread says he had the AI develop a working Bluetooth CUPS driver for his Canon Zoemini 2 mini photo printer. Canon only supports the printer from smartphones, so the driver made it usable from his Linux machine.
Connecting the agency's own MCP-based SEO service to Toby took an afternoon of wrong turns between desktop and web plugin setups, but once authenticated it created both monitored sites and completed full crawls: 44 pages for the law firm and 111 for the medical practice. Google data imports were still skipped because the service had no Google connection configured.
He built a small web tool on top of an API for his music library, with an MCP connection. He can ask the AI to check for missing artwork, sort out the genres, or fix the track numbers.
A university worker used AI to build a web version of a transcription program that used to need a special Windows machine reached by remote desktop. The new tool pairs a speech model with speaker detection on the university's own systems. Twenty minutes of interview audio now transcribes in 40 seconds with the speaker changes right, and students and staff can use it from a browser.
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.