Agents shrank his AI model container from 6 GB to 900 MB and off the GPU
LLMs migrated a 6GB GPU SciBERT container to a 900MB ONNX CPU container.
349 new ideas this week
Level up how you use AI
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.
Recommended a Patagonia winter jacket at a discount that turned out to
MBI Deep Dives asked the AI to buy a winter jacket; it recommended a Patagonia, then admitted the discount it had shown was no longer available. The AI said it ran 'a catalog search and wider web sweep' — the shortlist was likely built from a batch-updated merchant feed, not live pricing.
This one went wrong. See what happened before you try it.
My agent tracks my company's hotel booking deadlines and warns us three days before each one
A company worker set up a simple chain for hotel reservations. Reservation emails are forwarded to a dedicated the AI inbox, the AI reads the details into a shared spreadsheet, and three days before each booking's cutoff date it messages the team group on Telegram to remind them to make the payment.
The AI set up his Halloween lawn ornaments in Home Assistant in 5 minutes
The AI via MCP built a Home Assistant automation for Halloween lawn ornaments in 5 minutes, with a dashboard override button, and it ran.
The nanny logs her hours in an app he built, and it totals her pay each week against their contract
He built an app that lets their nanny track her worked hours in it, so the family does not have to keep track so closely. The app holds their contract details with her, including the exceptions for vacation and sick days, and gives a total at the end of the week for payment reconciliation. It is one of several small apps he has built for family life.
An AI assistant traced my family tree past 1,200 people and 13 generations
He set an AI assistant to work on genealogy sites and official archives to find his ancestors. It searches for a person with unknown parents, transcribes the record it finds, checks it against an official act and adds the new people to his family tree file, and the tree now holds more than 1,200 people across 13 generations on one branch.
An agent now flags which of our 2,000 receipts can be claimed
Arbisoft says its team used to check more than 2,000 receipts by hand. Now an AI agent flags what can be claimed on its own. The company says review time fell 56 percent and the change saves more than 800 hours a year.
800 hourssaved
My bots found grants local nonprofits did not know about
Eleanor Konik had the AI and AI team up on dashboards for local nonprofits. The AI did the early research and dug up grant chances the groups had not seen, like a group that pays for field trips to battlefields, a free textbooks program for private schools, and creative arts projects, and the lists were put behind a password for her friends to use.
Rebuild our website by handing the AI our brief and roadmap
The Causal team rebuilt its company website in three days by preparing a one-page brief, content architecture, references, assets and a task roadmap, then handing the build to the AI. Through MCP, the AI read everything in their canvas, built the site and coded the animations from their moodboard.
Failed to retrieve Hilton rates, returning a 'Something went wrong' error
Skift tested agents booking hotel rooms: The AI failed to retrieve rates and returned a 'Something went wrong' message on Hilton's Times Square page even after logging in with loyalty credentials, while Instinct succeeded across Hilton, Marriott, and Hyatt. Hilton says it isn't blocking agents — the failures read as technical.
This one went wrong. See what happened before you try it.
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.