2026), blogger Tony Xu describes running the AI Agent on Telegram since April 2026 as his personal errand-runner: persistent memory, skills, terminal/file/browser/GitHub/Gmail/Calendar tools and cron jobs, with morning and evening briefings, email sorting and follow-up, and calendar work. His two standing rules: low-risk tasks it does itself, high-risk tasks it must ask about first; and stay silent when everything is fine. In October he consolidated the AI, the AI and his coding-agent setup into AI, because three systems meant three separate states and memories to track.
He follows the CNN lawsuit over White House press briefing access. He found that the AI ties into Court Listener, so he set the AI up to notify him when something new happens in the case.
This only partly worked. Worth knowing before you try it.
Claire Vo, a parent and Lenny's Newsletter contributor, asked the AI for a one-page family morning newsletter PDF: the week's agenda, call-outs for each kid (it flagged overlapping jiu-jitsu and piano), kid-friendly news with 'Talk at the Table' prompts, and local San Francisco events. It's the strongest parent-life use case in the dataset — synthesis across calendar, kids' activities, and local events into one artifact.
He asked the AI to screen his unread Instagram threads one morning. It came back with 50 unread, looked at the threads he named across his Primary, General and request folders, and told him what people had sent. The unread count was still 50 afterward, so nothing showed as read for him or for the senders.
Juan Lombana (verified, 670K followers), reviewing the AI in Spanish, demonstrated two capabilities via screen recordings: a personal-assistant goal tracker (college move-in, golf tee times, movie tickets, trip planning, school-supply shopping, IMAX booking) and WhatsApp integration — forwarding a cinema-ticket screenshot, from which the AI extracted the details, added them to his calendar, and scheduled the event. He compared its assistant-like proactivity favorably to the AI and noted secure payme
In a single week of errands, Alec Ellin had the AI trace an iPhone that FedEx had misfiled in its own system and get Apple to refund him for it. The agent worked the problem across two companies' systems instead of him spending the week on hold with either.
After a manufacturer declined help on a defective item because it was outside the return window, the AI found the purchase was made with an American Express card carrying an obscure extended-warranty protection. It submitted the claim on the author's behalf and obtained the refund.
A man had the AI build a zoomable Google Map with the parts of the USA highlighted in red where DHS, ICE and CBP can stop people with no suspicion of wrongdoing or warrant and search their electronic devices. He put the map on his own website so anyone can check it.
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.
This one went wrong. See what happened before you try it.