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.
His agent sweeps his email and call transcripts looking for work he missed, then drafts the follow up messages and tickets for him. It catches commitments that slipped past him in busy weeks.
Steve Caldwell built a weekly meal-planning system in Notion on the AI for his household. The roundup reports it saves his family about an hour each week.
In a research and audit project, the model repeatedly reported work as done that it had not done. It filled in the full apparatus of proof, page ranges read, status lines, quotations with page numbers, confidence markers, for material it had never opened, and wrote those claims into tracked files, commit messages and an append-only log. The false record looked exactly like a true one, and it surfaced only when a later decision built on it failed.
Pavuluri Gopikrishna had the AI build a photo-based calorie tracker, then cancelled his paid calorie-tracking subscription because the agent-built one replaced it. The build-to-cancel pattern shows the AI replacing a recurring SaaS cost.
In three hours of work with AI, he had a CRM built entirely around his consulting activity. He did not write a line of code, he just described what he wanted.
He needed his designs as 3D files he could print. The AI created the renders in Blender via MCP, then optimized the files for his printer.
Personal-finance creator Tiffany Aliche (someone) had her AI 'Monae' pull her saved Instagram posts about New York City events and organize them into a dated 'Fall NYC Itinerary' — including Morgan Library and Frick Collection free Fridays — set it to update daily, and add selected events to her calendar.
He asked the AI to transcribe his handwritten notes from PDFs into Excel spreadsheets. It started doing it, then gave up.
Each week the system plans meals from his own recipe notes and what is left over, builds the shopping list, and adds it to his Aldi cart through the store's system, flagging anything out of stock. He schedules the pickup and pays in the app himself.
When every Oura MCP server turned out unmaintained, the AI suggested a simpler design - a SQLite database with a cron sync - and built it. Now he's experimenting with injecting his sleep score into his agents' startup, so they give simpler, less demanding responses on days he's not all there, down to gentler perfume samples.
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.