A random mix from the whole library. Shuffle for a new set.
A man built a service so his own agents can send physical mail. He has used it to submit credit card disputes, credit bureau disputes and a gym cancellation, the letters people put off because they mean printing, envelopes and a post office trip.
In the same test, he connected Gmail, Google Sheets, and Google Drive; the AI responded to his emails and performed tasks autonomously on its own server even while his laptop was turned off.
He connected his Gmail to an AI task that watched every new email and was only allowed to interrupt him when a message needed action or came from family, with a draft reply ready. All afternoon it alerted him three times, for a bank message, a family email he answered from its draft, and a ticket itinerary change he needed to act on.
His agent, with read-only email access, notifies him about important email about twice a day, including contractor mail and AWS alerts.
Hemant Kadam, demonstrating his 'craziest use case' after a couple of days on the AI, opened the app to a Sarvam DevOps Engineer application page. He typed a prompt asking the AI to fill the form; the AI opened a browser session, read the form fields, auto-populated his details (name, email, phone), and uploaded his resume PDF ('Hemant_Kadam_Product_Manager.pdf').
Setting up the Instinct assistant live on screen, he had it book him a slot at his local recycling centre. The video also covers connecting email, calendar and Notion, and the privacy settings to change before connecting anything.
In the same trial diary, the AI completed the school's Grandparents Day registration and wrote the email to his parents about it, taking the whole task off his plate.
Agent manages the import and export process for the international move of his pet, including comms and form filling, and corrals the family's move documentation.
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.
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.