A random mix from the whole library. Shuffle for a new set.
A builder used AI to make a 'describe your situation' tool over Australia's official welfare pages: it takes a one-sentence description, works in 24 languages and shows which Services Australia payments might apply, each linked to its official page. Across 43 test questions it invented zero payments and refused correctly 100% of the time, with payment recall of 0.76.
He set up an automation to email himself a daily update from his calendar. Every run fails at the send step with a safety block, even with his Gmail connector set to allow all tools, while asking in chat sends fine. He rebuilt it several ways and every version stops at the same point.
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.
She was using AI to archive legislative material when it flagged a serious vulnerability in a state legislature's website. She had to stop and report it.
X user someone (Charlie) gave the AI inbox access at the start of a deep personal-data experiment. In one of the standout moments, the agent surfaced an important message he had missed, drafted a response, co-edited it with him, and sent it — an agentic loop (find, draft, revise, send) rather than a one-shot draft.
Outside code, his biggest win is boring paperwork. The AI filed his reserve duty refunds, sorted out his national insurance payments and did his flight check-ins, working in his own logged in Chrome. Each job is about ten minutes of work, which is exactly why he kept putting them off. He gives each area of his life its own folder with a CLAUDE.md and a notes file, so the money stuff does not mix with the rest.
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.
During a 30-day trial diary, the author shows the AI filling out a school field-trip permission slip it had found in his email — one of several family-admin tasks it handled from his accounts.
She asked the AI if it could cancel her Mint Mobile account. The company's chat agent had told her she needed to call in. She gave the AI her Mint details, the AI opened its own chat with the company and got the cancellation done, with no phone call and no talking to people herself.
He pointed the AI Fable at a newspaper archive and asked for a timeline of wildfire events in and around the Adirondacks. The result is an interactive timeline built from 12,000 pages of newspapers.
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.