Gemini's task automation is here and it's wild
Briefly

Gemini's task automation is here and it's wild
"Starting with food delivery and rideshare apps, Gemini would be able to use certain apps on your behalf in a virtual window to take care of things like ordering dinner or getting a car to the airport - all based on simple prompts. You know, all the stuff that we've been promised for years AI assistants will be able to do."
"Gemini asked for clarification to determine which airport (a good question to ask!), then it went through a couple of steps on its own: adding the destination and opting to skip the step where you specify your airline, which doesn't really matter at my local airport since it's all in one terminal. As promised, the system stopped before the final step and prompted me to review the details before putting in the request for a car."
"A vague and slightly more complicated request to order a coffee and a croissant required a little more input from me - and a lot of time on Gemini's part scrolling through Starbucks' hot drink options - but sure enough, it found the flat white on the menu. It also confronted a crucial decision: order the chocolate croissant warmed, or straight out of the pastry case? Without my input, it specified (correctly) that the pastry should be warmed."
Google and Samsung introduced task automation for Gemini, enabling the AI assistant to perform actions within apps on behalf of users. Starting with food delivery and rideshare services, Gemini can handle requests like ordering dinner or booking transportation based on simple voice or text prompts. The feature operates in a virtual window, allowing users to review details before final confirmation. Early testing shows Gemini successfully navigating app interfaces, asking clarifying questions when needed, and making reasonable decisions about order specifications. The system demonstrates significant improvement over previous AI assistant capabilities, handling both straightforward requests and more complex scenarios requiring menu navigation and decision-making.
Read at The Verge
Unable to calculate read time
[
|
]