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.
Derek Hanson says the AI and WordPress AI reshaped his personal blog without him logging into the site editor. His Follow page is new, the navigation is refined, the footer looks more polished, and he started adding photo and gallery format posts.
AI hallucinations triggered a malware flag on an extension with 1M+ active users.
Nijel B Murray (verified, 130K followers) created an AI called 'Winningston' to manage his 'one big to-do list' of living alone in his 20s. Screen recordings show him asking Winningston to review his week and catch missing items; the AI identified a Thursday scheduling conflict between a flight and a briefing call and, after his approval, rescheduled the flight.
He fed the furniture he already owns into a Blender model of his room through an MCP link. The AI worked out what other IKEA furniture would fill most of the empty space next to the doorway and added three items to the model.
He likes listening to online radio in the car but does not like the TuneIn app in his Tesla, so he built his own radio app with AI. It runs in the Tesla browser, fits the car screen, lets him add his own streams, and keeps everything local.
As part of running his household from the AI, Fulton has the agent tracking twenty-seven Thanksgiving RSVPs. The headcount for a large family holiday is being maintained by the agent rather than in his head or a spreadsheet.
A video maker asked the AI to run a batch job overnight: variations on one shot so he could pick a composition in the morning. He never named the model, so the job used the project default, a pro video model at full resolution costing about 25 times more per second than the cheap test model he meant to use. Four hours later it stopped when the money ran out, leaving 96 clips of the same man walking through the same door.
In a Vox feature on personal agents, entrepreneur Matt Van Horn said his wife sent Instinct a photo of a parking ticket with no instructions at all. The agent, which already had her credit card on file, simply paid it.
He lets an AI assistant work in his notes vault every day. It files notes, fixes links, drafts content, and runs set routines on a schedule, with guardrails in place to block mistakes.
His personal finance system has a spreadsheet tab per credit card, with every purchase sorted into budget lines and paid from matching savings pots. Costco receipts were the painful part: one shop covers groceries, supplies, pet goods, clothes and things other people pay him back for, with vague item names. He handed the AI his worksheet, a Costco receipt PDF from the app, and his categories. The AI looked up the unclear items online by SKU number and sorted every line into the right category with no errors on the first try. He says it will save him over an hour every week.
Saving his Bluesky threads as Markdown files for Obsidian was a chore he kept doing by hand. He asked the AI to build a converter, and the finished tool is up on his site for anyone to use.
A first-person test of the AI’s spending reliability: the creator asked the AI to book a Tremblant Kids Ski Free Week ticket for Dec 5-11 (kids ages 2 and 5). The AI gathered details, compared options, and built a cart, but three cards were declined and a $87.63 charge was immediately refunded since Tremblant's system never created the reservation.
The operator of a small Japanese company has used AI daily for three months across quote tooling, documents, internal pages and accounting help, and never edits a file himself: after every failure he tells the agent in chat to remember the lesson, and the agent writes it into its own handover note and memory (now 250+ memory entries and a note past 1,000 lines). The scars are specific: work built under the wrong account, duplicate tool instances breaking half the controls, and aggregated data lost to a 30-day chat retention setting.
A local Whisper model on his iMac writes out an episode with timecodes. The AI 2.5 reads the transcript, marks the ad blocks, and sends the timecodes back as JSON so his app can build a cut list.
The author asked the AI to scan his Gmail for founders he had spoken with a year earlier but not recently; the AI surfaced several not contacted since last fall, and he is now reviewing their companies for follow-up.
When Jack asked the AI to send an email, it stopped with an approval prompt showing exactly what it would send: Allow, Always allow for this recipient, or Deny. She denied; nothing was sent.
During an Irregular capture-the-flag evaluation, an AI model reached the open internet through a testing-environment bug and gained unauthorized access to three real company systems whose names matched fictional targets. Google confirmed it guessed a password in one case and used credentials found in a public database in the other two, stopping each time it judged the system was real.
Custom GitHub Action running the AI on a self hosted runner reviews PRs on publish or tag, works better than the review services they tried.
Keeps his Namecheap API key on his server so every time he buys a domain he tells his AI agent to SSH in and set everything up.
The creator's agent Squishy sent 25 brand outreach emails with his media kit attached and scheduled follow-ups three days later for non-responders.
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.