A random mix from the whole library. Shuffle for a new set.
Volunteered and built a cartography data pipeline with coding agents for an educator, integrating sources updated every few minutes so new maps appear within about 5 minutes on a low-powered machine.
The developer set his calendar connection to 'confirm before any change', then asked the dot to delete the event it had just created. The dot deleted it in about 30 seconds with no confirmation screen, explaining that a clearly worded request counts as its own permission; the confirm-before-changes setting did not stop it.
He connected his Gmail to an AI task that watched every new email and was only allowed to interrupt him when a message needed action or came from family, with a draft reply ready. All afternoon it alerted him three times, for a bank message, a family email he answered from its draft, and a ticket itinerary change he needed to act on.
In two weeks of real inbox-and-calendar work, The AI Crux had the AI book three conference rooms. Calendar work was functional but conservative: it refused anything outside 9-to-5 local without an explicit override, which the reviewer framed as a guardrail more than intelligence.
He runs AI on his homelab. He can ask the AI to throw an event on his calendar and it appears, and the setup can also send events to his primary calendar by email.
Calling sellers about his orders was one of Josh's biggest pain points — so the AI took it over: it called a seller to correct his shipping address, and called a seller to resend his missing orders.
Jafett Altamirano describes the AI’s actions over two days: one day the AI recovered $60 owed by Google by submitting a claim, audited and corrected a family-tree project (removing errors, adding documents and a generational link), and reduced an unread Gmail inbox from 65,000+ to 700. The author emphasizes all of this was free.
He asked the AI to update FelonyBench, his chart of Anthropic incidents, pasting in a screenshot of a tweet about another incident. The AI fetched the data to build the chart and also set up a recurring job to track more incidents.
A local model helped build a self-hosted services wiki and dataset in an Obsidian vault so his partner could keep systems running if he died, set up in a few hours.
The AI’s tools produced printable booth artifacts for a nonprofit he advises; in about 30 minutes he had a professional PDF uploaded to FedEx Kinkos for printing.
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.