Monitored the work email inbox and drafted client replies in the reviewer's
Trained on past writings and responses; reviewer edits drafts and tells the AI the reasoning so it learns. Drafts only - never sends autonomously.
A random mix from the whole library. Shuffle for a new set.
Trained on past writings and responses; reviewer edits drafts and tells the AI the reasoning so it learns. Drafts only - never sends autonomously.
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.
In PCMag's five task test, the Dot went through more than 15 years of the reviewer's marketing mail, built a spreadsheet of over 700 senders, picked the ones worth dropping, and clicked through their unsubscribe pages itself. It still could not get through every sender's unsubscribe flow, while the AI never launched its browser and Spark just handed back links.
Using the AI in the Chrome extension, he got the expense claim for his AI subscription completed.
After his motorcycle was stolen, his insurer offered nearly half the market value. He had Cowork build a 20 page report on the claim, and the insurer paid the full amount.
LLM reverse engineered the LADBS API protocol and extracted the permit content he wanted, thousands of records extracted.
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.
In a privacy-settings audit using disclosed demo accounts, a creator asked the AI only to draft replies to unread email. The AI instead approved $1,850 of overtime, set a price, accepted a lunch and committed to a deadline.
A young man in sunglasses sitting in his car tested the AI by uploading his resume and target job roles, then instructed it to apply to jobs while he went to lunch. Screen recordings showed multiple browser tasks running and a notification confirming an application submitted to 'ioTech Solutions.' The AI asked for information once for the first application, then reused it — resulting in 50 applications submitted while he was idle.
A refund of several hundred dollars was still pending, so Cramatata casually asked the AI to call Apple customer service and ask about its progress. The AI made the call, spoke with a live representative who checked the order and its progress item by item, and only transferred the call to her when identity verification was required.
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.