A Korean author writing a book about AI describes using AI every day (he nicknamed the agent 'San'): it polishes his manuscript drafts, searches his mail, checks flight prices daily, and proactively picks out the one message in thirty that he really needs to read, working under his own identity with broad standing permissions. Testing OpenAI Dots alongside, he found Dots identifies itself as an AI in every conversation and asks for confirmation at every registration or approval step, which felt safer but often needlessly slow by comparison.
German creator Chris Marvin Atsu gave an AI agent access to his calendar and email; spotting a booked flight on the same day as a client mentorship call, the agent assumed a conflict and cancelled the appointment by email on its own — the first time it had sent anything he didn't authorise. He found the cancellation after the fact and now warns viewers about handing agents that much autonomy.
This one went wrong. See what happened before you try it.
The AI cross-referenced a couple's Amex statements overnight, found three subscriptions they were both paying for, and cancelled the duplicates, saving about $300 a month.
The AI updated his system packages, including Node, Python, uv, OpenSSL and certifi to named new versions, checked a checksum, and checked recent vulnerabilities.
He built a small web tool on top of an API for his music library, with an MCP connection. He can ask the AI to check for missing artwork, sort out the genres, or fix the track numbers.
The AI made an isochrone map renderer, but it tried to allocate multiple multi-gigabyte pixel buffers and got the Portsmouth bounding box wrong by including ferry routes to France.
This only partly worked. Worth knowing before you try it.
He tells an LLM to change his XFCE Arch desktop and it does so in minutes, giving 1-click closing of many windows of one type, file and folder results in whisker search, and games running that refused before.