Turned PDF attachments into calendar events
One of the demonstrated workflows in '11 Ways I Actually Use the AI (Real Examples)', shown via screen recordings.
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.
One of the demonstrated workflows in '11 Ways I Actually Use the AI (Real Examples)', shown via screen recordings.
In one day the AI accidentally deleted one of his GitHub repos, which he says was partly his own fault for not explaining himself better. The same day it also failed to spot the cause of air bubbles on his film negatives, which he found himself by searching the web.
A Deaf creator recounts waking up after missing an early-morning Air Canada flight and asking the AI to find a cheaper replacement. The AI accessed his Air Canada account, confirmed his Flex ticket could be changed, searched other airlines' prices in parallel, and supplied the airline phone number he could not find; he called via Canada VRS, found Air Canada's own rebooking cheapest, and paid — about 30 minutes total versus an estimated one to two stressful hours alone.
Slack fix-it button tells the AI to fix an issue in his app, run tests, UI test with computer use, and deploy it.
His AI, which he calls Quasar, signs into his Blink account each night and pulls the day's motion clips from the feeder camera. It stitches the clips together, picks out frames, takes a try at naming the birds, and keeps a dated catalog and a running yard list of confirmed birds only, and he approves any Facebook post before it goes up.
A local publisher’s the AI research, write and sell the ads for a Thursday paper read by 6,000 neighbours. The bots cover the whole production loop of a real local news product, not just the writing.
He set up an AI that wakes up when a new the AI release lands. It reads the changelog, picks out only the parts he cares about, and sends him a DM when there is something of interest.
The AI wrote an MCP setup script whose cleanup step wiped the existing project when run, with no backup.
LLMs decompiled Civilization 1 into reconstructed C source that builds with the original toolchain and matches the original executable byte-for-byte except a four-byte patch correction (finished result report).
A business owner runs a six-bot the AI back office for $200 a month, compared in his post with a $58,000 hire; the desk works his inbox finds and holds a veto on any money leaving. The setup is specced like a small office: named seats, a shared brief, and one bot whose job is to say no to spending.
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.