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.
A renter fed the AI his lease, the deduction statement and move-out photos after a landlord withheld a $1,200 cleaning fee from a $2,500 deposit. The AI checked California law and wrote a dispute letter citing the statute, and he recovered $950.
Reverse engineered his supermarket API and made a custom MCP to automate grocery shopping; now fills his cart through AI.
Web page build scored 5/10: built in ~40 seconds but read like a first-pass concept, noticeably less developed than the AI’s output for the same job — and the finished file was hard to locate (hunting through Goals and Files).
Joao Silva installed the Jev decision-model skill into his AI fleet without writing integration code: he pasted a plain-English instruction into a session and the agent copied the folder, found the right .env file, added the key and ran the checksum verification. The skill then passed his mandatory three-reviewer gate (security, QA, technical writing) before being committed.
Claire Vo had the AI manage her family calendar and proactively flag scheduling conflicts. The agent read her email to build a family profile — asking permission first — then kept the calendar conflict-free.
Kantar's People Team split HR data preparation into subtasks and gave each to an AI Studio agent: one located documents, another translated everything to English, a third found duplicate policies and drafted formatted versions. Ten agents cleaned, tagged and organized 4,000 artifacts into 400 policy documents in six weeks, grounding the firm's new HR advisory agent.
Dave Y. Kim reported spending about 30 seconds on the AI to start a flight-disruption reimbursement that played out over several days and returned $2,000.
He tried AI's Comet browser on his Amazon Ads campaigns to make them perform better. He says it raised his ROAS by 120%.
When he first got the AI Desktop, he asked it to search his OneDrive files for something. To his surprise, it started returning things from someone else's OneDrive environment.
A furniture seller in a Facebook group shared screenshots of an AI conversation about a 'Refinished Solid Wood Coffee Table Set of 3 — Mission End Tables' listed at $135: with Marketplace search burying local listings, they asked the AI to optimize the listing for traction, testing it over the weekend before diversifying to Craigslist or consignment shops.
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.