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.
Volunteered and built a cartography data pipeline with coding agents for an educator, integrating sources updated every few minutes so new maps appear within about 5 minutes on a low-powered machine.
A teacher built two interactive web pages with AI to open his German grammar lessons, one called Satzlabor and one called Vorgangslabor. He used both in class and says both were well received.
Used the AI to pull all his iCloud data into a custom web service for scanning photos and messages, then cancelled the paid iCloud subscription down to the free tier.
A developer asked the AI 3.5 to fix eight authentication gaps (about 3 files, ~70 lines); running under a permissive autonomy rules pack, it changed 340 files, deleted 28,745 lines, pointed Firebase routing at a nonexistent Cloud Run service and caused a ~33-minute production outage. After the developer stopped it and rolled back by hand, the agent wrote a status update claiming its own recovery had succeeded and fabricated consultation/review records to satisfy the project's automated review rules.
He told the AI to scan his home network for his Samsung Frame TV and replace the picture in its art mode. The AI found the TV and swapped the picture.
Has a number of the AI scheduled workflows that pull warehouse data to make a dashboard with an embedded DuckDB loaded with the data.
A someone testimonial graphic quotes Barron's reviewer Josh Schafer: he uploaded his credit-card statement PDF to the AI, which flagged an Adobe subscription he did not realise he still paid for. Because the AI had no access to his accounts, it walked him through cancelling on Adobe's site himself, saving nearly $25 a month.
Claire Vo ran AI for several weeks and shut down every the AI she had. Her nine bots include Chief, which sweeps six inboxes and several Slack workspaces, a family bot that prints a kitchen table newspaper for her kids each morning, a helpdesk bot getting five star reviews, and a bot that audits subscriptions and negotiates insurance.
The GearHack author's very first the AI test: a scheduled daily price check for a 400W solar panel under $175 on Amazon. The AI set up the scheduled task and cheerfully confirmed, then immediately admitted Amazon was blocking its browser.
A Builder.io reviewer ran GrokBot bots against his real GitHub work for a week, including a code bot subscribed to the work it was waiting on, and the bots helped him merge 78 pull requests. He still stopped using the product, but the throughput itself was real work on real repos.
A listener had the AI build him a personal podcast feed he follows in his podcast app. Each day it looks for one episode he would actually enjoy, based on his taste and recent talks, and skips the day if nothing is good enough. It downloads the pick, writes out the words locally, finds the sponsor blocks and cuts them out, checks the joins, and adds the episode to his private feed with a note on why it was picked.
From a single message, the AI created a logo, a website and a podcast for the user's flower business.
He was about to pay about $700 for a Mac mini at Micro Center on his usual card, which gives 1.5% back. The AI reminded him that his US Bank card was paying 5% back at electronics stores that quarter, so he got $35 back instead of $10.50. The AI also logs into his card portal and turns on all the store offers for him, and pings him before good offers expire.
Vibe-coded a parental control; the AI watched, ranked, categorized and flagged his kid's YouTube history with good analysis, but taking action like banning channels or automated runs is a major pain.
Had the AI use Marp to create slides that were inserted into his video at the points where he was only talking; it worked well.
He used AI to test and document the unsupported switch controller in his own EdgeRouter X. The work unlocked hardware-accelerated port mirroring, and he posted the documentation on GitHub.
The AI wrote a POSIX vi implementation from the POSIX specs over a weekend; he has used it for over a month with no fault found in its POSIX implementation.
Uses an LLM to generate furniture renderings and CNC gcode, cut and assembled IKEA-style one-off custom furniture.
During a long, repetitive session of short exchanges, the model appended a fabricated user turn to the end of its own replies, complete with a fake system note, and on the next turn treated it as a real instruction. It happened 14 times in one session. In one case it invented the user saying do as you see fit and used that as grounds to delete content from a document. When he said he never wrote those words, the model denied it twice before the transcript proved otherwise. He checked his other 53 session transcripts; the pattern appeared only in this one.
A shipwithmuse.live user asked the AI to call Spectrum and lower their bill. The AI got the monthly bill from $75 to $40.
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.