I updated a client's email triage so it forwards mail to her customers
He updated an old email triage workflow for a client this weekend. Jev now runs alongside GPT-4o mini, which still controls which emails get forwarded to her customers.
A random mix from the whole library. Shuffle for a new set.
He updated an old email triage workflow for a client this weekend. Jev now runs alongside GPT-4o mini, which still controls which emails get forwarded to her customers.
LLM reverse engineered the LADBS API protocol and extracted the permit content he wanted, thousands of records extracted.
The AI sent a notification that it had spotted an email from TripIt, the vacation-planning app Ulanoff uses, about a password change he had forgotten making. The agent wanted to make sure he'd seen the email verifying it was him.
The author describes using AI to resolve a six-month-old travel medical insurance claim with Cigna. The AI called the insurer, was transparent about being an AI, conducted the call politely (impressing the representative), and — because final consent was required — called the author's phone and connected the parties so he could approve verbally.
Three family members, three nationalities, one move to Brazil. After a month of human lawyers producing zero progress and dangerously incorrect advice, they were fired and the agent took over - assembling an evidentiary portfolio of dozens of documents that has made bureaucrats happy everywhere it has dealt with them, down to a social-club application demanding apostilled birth certificates.
Across the same two-week inbox-and-calendar test, the AI proactively flagged every one of the author's seven calendar double-bookings before the meetings occurred.
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.
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.
His agent sweeps his email and call transcripts looking for work he missed, then drafts the follow up messages and tickets for him. It catches commitments that slipped past him in busy weeks.
He got the AI to build out a structured dataset of all 4,925 vacancies, with job titles, organisation, salary and location. He shared it in a spreadsheet for other people to play with.
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.