Gemini’s task automation is here and it’s wild

The Galaxy S26 Ultra is one of the first devices to offer the feature.

by Allison Johnson

Mar 12, 2026, 4:59 PM UTC

Computers ordering cappuccinos.

Photo: Allison Johnson / The Verge

Allison Johnson is a senior reviewer with over a decade of experience writing about consumer tech. She has a special interest in mobile photography and telecom. Previously, she worked at DPReview.

A couple of weeks ago, Google and Samsung announced a big Gemini development coming to their newest devices: task automation. 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. That feature wasn’t live when I first started testing the S26 Ultra, but it just arrived in beta as part of an update. And boy is it weird watching your phone use itself!

The first prompt I gave it was pretty simple: order an Uber to the airport. 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.

<em>You have the option to watch Gemini go through its steps, and you can take control or stop the automation any time.</em>

<em>Gemini will ask any necessary follow-up questions.</em>

<em>Gemini talks itself through its next move.</em>

<em>If your attention is elsewhere, you can tap the icon at the top of the screen to check progress.</em>

<em>The feature is designed to leave the final step up to you.</em>

1/5

You have the option to watch Gemini go through its steps, and you can take control or stop the automation any time.

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. Pretty impressive for an assistant that just a year ago would argue with me over the details of a flight on my calendar.

I’ve got much more testing to do with this automation feature and I plan to spend the next few days throwing it some curveballs. Still, it’s impressive to see this feature out in the wild working as intended — so far, at least.

Photography by Allison Johnson / The Verge

Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.