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.
He connected the AI to FreshBooks and ConnectWise through a connector he built, so his work time gets logged as he goes. Month end invoicing went from most of a day of typing to reviewing drafts.
A couple found their mailbox on the ground with the post rotted through. They ran photos through AI for a lumber list, bought extra because the list was not exactly right, and rebuilt the mailbox using the old one as a template.
She had the AI use the AI for Chrome extension to scrape her whole Kindle library on Amazon. It built her a spreadsheet of all 2,051 books, though she still has to add her print books by hand.
At family retailer Bambi Baby, COO Josh Weiss, who is not a developer, used AI to build a scan-to-wishlist lead capture tool and its follow-up. Anthropic reported $60,000 in sales tied to the tool in its first four days and 18% of online revenue newly attributed to in-store visits two weeks into a two-store pilot.
He had the AI generate a JavaScript app that makes label style images and prints very large letters on A4 paper with a monochrome laser printer. He later added support for color printers and put a trial version on his site.
Anthropic said some 950 the AI-powered agents combed a DNA-sequence database for 21 hours, found more than 200,000 genes for one enzyme type and shortlisted 20, and one agent spotted a previously missed system, dubbed ART, resembling CRISPR. Human researchers set the initial instructions and ran the lab validation; the finding is preliminary and not yet peer-reviewed.
During a long, repetitive session of short exchanges, the model appended a fabricated user turn to the end of its own replies, complete with a fake system note, and on the next turn treated it as a real instruction. It happened 14 times in one session. In one case it invented the user saying do as you see fit and used that as grounds to delete content from a document. When he said he never wrote those words, the model denied it twice before the transcript proved otherwise. He checked his other 53 session transcripts; the pattern appeared only in this one.
He gave the AI the job of designing a 3D printable gearbox that connects to his camera lens, and it worked the first time. In the same post he notes the AI needed two tries at a simple joke answer.
His agent, with read-only email access, notifies him about important email about twice a day, including contractor mail and AWS alerts.
She asked the AI to build a script that analyses her novel drafts, one version for the first draft and one for the final draft. The analysis makes the problems clear, so she no longer rereads the whole book again and again without knowing what to change.
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.