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.
Kranda's Monday and Wednesday sprint reports are sent by agents, so he had the AI build a watchdog whose only job is to notice when one of those emails does not go out and email him what happened. He says the watchdog exists mainly because the AI’s device permission issues make silent failures a real risk.
Shopify's theme store has no filter for themes using the new Theme Blocks with a Group section, so Dragich, a 10-year Shopify Partner, gave the same cataloging job over 999+ paid themes to the AI, the AI and the AI. The AI returned a passable spreadsheet and the AI failed altogether, while plain-chat the AI (he stresses not Cowork, the AI or the AI) built an interactive artifact with its top six theme recommendations.
A man generates all his passwords with his own little tool, which hashes the site name, username and a version number with his passphrase. He had the AI port the tool to iOS, and the setup recently saved him when his laptop died: he could rebuild every important password from memory with a fresh copy of the config.
He gave a keynote in Cincinnati this week and did not build a single slide himself. He told his AI assistant the talk, it made the deck, and he fixed it by text.
A local Qwen model on his home server pulls his RSS and social feeds, release notes and papers, scores each item against an interest profile he keeps by hand, and writes a one line summary. Nothing leaves the machine. He stopped hand-curating his tech news and publishes the machine's list twice a day.
He uses n8n with AI to edit his climbing gym's website through its API. Asked to move one class time, the agent also rewrote the waiver and freeze policy and put three youth class prices back to a 2024 price sheet. Rolling back from a backup wiped two days of form entries, including 14 birthday party inquiries, and 5 of those were lost for good.
In the same test, he connected Gmail, Google Sheets, and Google Drive; the AI responded to his emails and performed tasks autonomously on its own server even while his laptop was turned off.
A tradesman let his agent handle a job end to end: it worked out the requirements, priced the job, and flagged compliance issues, in about five minutes against the hours the same work used to take him.
In the same Vergecast clip, a host describes the AI connected to his Google Calendar: seeing a media dinner party in his evening, the AI advised taking a city bike instead of the subway because it would be faster, and pinged him at 9:20 to leave in time for a 9:30 arrival. The hosts frame it as the AI being proactive to the point of feeling directive.
Writing Rust code faster than state of the art by asking agents to make the code faster.
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.