Agents swapped a fan shroud section inside a 3D model file, perfectly
The AI and Antigravity took an existing STL and swapped a fan-shroud section for another design by directly manipulating the STL geometry in Python; it went perfectly.
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.
The AI and Antigravity took an existing STL and swapped a fan-shroud section for another design by directly manipulating the STL geometry in Python; it went perfectly.
A session generated a Word document with a script. The user then edited the document in Word for about 40 minutes and saved. When he asked for one more change, the session re-ran its script, which rebuilt the whole file from its older in-memory content and replaced the file on disk. His 40 minutes of edits were unrecoverable, because the write went through the shell, where the tool’s read-before-write protection does not apply.
A shipwithmuse automation recipe has the AI build an Instagram content studio: the agent clusters the user's last 100 posts into content lanes, builds an ideas dashboard, and runs a weekly scheduled trend check.
He resells Amazon liquidation pallets on Facebook Marketplace. With the AI he built one system for the whole flow: before buying, a browser extension pulls a lot’s manifest, retail prices and photos and says whether the lot is worth the asking price; after buying, it generates the Marketplace bulk upload files with pricing; in his garage he checks items in, photographs damage on his phone and prints QR labels; and dashboards track sales, tax, profit and sell through. It is about 10,000 lines of code across more than 35 versions, running on his home server.
~500 real cases categorized: money 98 (20%), work 84, admin 60, travel 56, shopping 51; 12 agents joined the first morning. Quoted standouts: $3,500/yr car insurance switched in 5 minutes, $1,900 HOA refund, $44.99/yr forgotten subscription cancelled, PODS booked $576 under quote.
He had the AI build an Excel sheet of car models that could work as his next car, using his own list of must haves. The sheet came back with 65 options, with size, comfort and whether each one comes as an automatic.
LLM agents turned traced schematics into Verilog models of a 1978 Lexicon, with many mistakes found and fixed over months.
He uses AI to keep track of his GLP-1 dose history. It also makes a chart of the estimated concentration over time.
His talk archive site had been a work in progress for years. He asked the AI to help track down records of talks he has given, and the site now contains 115 presentations covering 26 years.
Built tooling so an LLM manages his investments long term: auto-deploys new cash by his priorities, implements tax-loss harvesting (GitHub investbot).
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.