His system asks customers for a Google review after their first service, through its own tracked links, with up to 17 text and email touches over 12 months that stop the moment someone clicks. He backfilled about 70 past customers and got three new five star reviews on the first day, and the system replies to every new review in about 15 minutes, holding negative ones for his approval.
A site owner pointed the AI at his site sublunar.space for an hour. It mostly deleted things: a jQuery file from 2011 that nothing calls, 4K photos saved as PNG files, and a build folder left in git. The cleanup cut 73,657 lines and about 23 MB of images.
An LLM generated an entire compiler for his new language over 7 months of iterating and fixing, generating WASM runnable in a browser playground the LLM also built.
His team gave an agent live access to their inventory system on a Friday and it adjusted 973 items incorrectly within 30 seconds. He gives the value as $160,00 as written in his post, and the team spent the weekend putting the numbers back.
This one went wrong. See what happened before you try it.
A man who flips vintage items on eBay connected the AI to his store. The AI found 28 listings with views but no sales, worked out that eBay was really taking 16% in fees, and published a bundle of two vases that sold within a week.
Tony Xu recalls using AI as his always-on agent in early 2026: he handed it a blog post draft task over Telegram, and the AI cloned his repository, studied his older articles for structure and voice, drafted the post, and he then checked the structure, facts and wording before publishing. He liked the capability but quit over the upkeep: a self-hosted gateway and services he had to run himself.