A random mix from the whole library. Shuffle for a new set.
A parent says the AI goes through his kids' Google Classroom and tracks their homework in every class: due dates, missing work and scores. It then sends the kids a daily email on how they are doing, with a daily plan to stay on top of their work.
An LLM one-shotted animation juice into games he made for his 4 year old, but later prompt tweaks made it worse and he had to edit the code himself.
A father of a 5-year-old used AI to generate a fresh bedtime story every night, sometimes with audio mode reading aloud - until his daughter started asking for 'that story we listened to before' and the favorites were buried across scattered chat threads. He built a small website, FifiStory, as a persistent shelf: the stories live in one collection that can be read or listened to, and he keeps adding to it as they use it. He made it free and public, no account or paywall.
In the same roundup, Jason Zhang listed a bonus feature: sending messages to friends via connected Messenger and Instagram accounts.
He had the AI put together a big brief on summer day camps that take 5 year olds within a 15 minute drive in rush hour of his zip code, with one Spanish immersion camp. He read the options, checked drive times and the camp sites himself, and says the three camps they went with were great and close.
He let his daughter chat out loud with AI to make a game, and the AI gave her small kid sized coding lessons along the way. They put the game on his Raspberry Pi box with an Arduino joystick, so she can play it whenever she wants.
Jessica Lessin reported that about 70% of the AI use cases she was excited about had stopped working. Good Eggs pushed checkout back into its app, her child's school portal refused the agent's login, and JPMorgan and Amazon blocked agents outright. Segment starts at 15:16.
The AI produced a thirteen-page strategic assessment of Fulton's father's retirement community. Its pickleball court count was verified from satellite photos — eight dedicated courts, checked, in his words, from orbit.
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.
Anthropic's Project Swap sent 201 employees' the AI-powered agents onto a digital trading floor to pitch, haggle and strike book-swap deals. Agent preference rankings matched their owners' on 61 percent of book pairs, and staff ended up with roughly their fifth choice of ten; most of the shortfall came from misread preferences, not bad bargaining.
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.