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.
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.
The same man took a photo of a clock this morning and asked the AI to buy replacement batteries. The AI identified the clock from the photo, found its instruction manual, worked out which batteries it takes, and ordered them from Amazon.
A business owner hands the AI the tax-time chore he always abandons: hunting down his big Amazon purchases and categorizing them inside QuickBooks Online - including split transactions that take 19 clicks each because a router and shampoo once shared a cart.
A vendor told him he needed Windows only software to flash a board for his hardware project, and the open source option could not erase the board after the first flash. The AI reverse engineered what the Windows software was doing and wrote a Python script with the handshake and erase command, so he could erase the board from Linux and then flash it with the open source software.
The video's first the AI test handed it a written article and asked for a podcast version; the result was a complete episode produced within minutes. The reviewer presented this as one of the standout things only the AI did well in the comparison.
Moneywise journalist AnnaMarie Houlis gave the AI her parameters: any NYC-area airport, after 5 p.m. on Oct. 26, carry-on only. The AI returned a reasoned lineup: its pick, a $595 Turkish Airlines flight from JFK (8:40 p.m., 14h45m); the cheapest, a $462 Royal Air Maroc with a 33-hour Casablanca layover; and the fastest, a $725 Air France from Newark (10h45m). She kept the research but booked herself, unwilling to share card details after reported the AI security vulnerabilities.
Liang Gou wrote no code himself: he directed the AI to design and build a complete grading app for his wife, a high school math teacher grading 100+ papers a week at 3 to 5 hours per test. The rubric engine reconstructs a rubric from a single graded example, its eval bank comes from real AP Calculus AB free-response exams, two models cross-check grades, and the agent tested the app itself in a browser before deployment.
He had the AI watch his online trainings and take the tests for him, and he collected 40 certificates in one day. He told it not to get perfect scores every time, and he says the system is broken if this works.
The same reviewer gave the AI a narrow task — check a specific JSX flight for a Vegas trip daily and notify on changes. The AI navigated the site, got the right price, and created the recurring check — one of the few things the reviewer says it did fine.
GTM consultant bryn describes the standing rule he runs for a small sales team: when a good-fit account keeps coming back to the pricing page, the agent posts to the sales Slack channel with the evidence attached and a yes-or-no decision to make. The point is that reading and assembling evidence is the agent's job, not the rep's.
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.