Gemini is getting its first agentic capabilities
Briefly

Gemini is getting its first agentic capabilities
"Starting with some Pixel 10 phones and the Samsung Galaxy S26 series, Gemini will be able to hail an Uber or put together a DoorDash order on its own. It's called task automation, and it starts with a prompt to Gemini - something like "Get me an Uber to the Palace of Fine Arts." Gemini then launches the app in a virtual window on your device and goes through the process step-by-step."
"According to Android ecosystem president Sameer Samat, this is one step on the journey from thinking of Android not as an operating system, but as an "intelligence system." And app automations aren't strictly limited to Gemini. Samat says that this ability for an AI assistant to automate tasks is coming to Android's next major release, so we can expect to hear more about it as more is revealed about Android 17."
"The demos I saw were based on Gemini 3 opening the app and using reasoning to click through the various steps, find the right options, and consider alternatives. But app developers can also expose certain actions using MCP or Android's app functions framework - Google's been laying the groundwork for the latter since at least 2024. Where neither of those things exists, the idea is that Gemini will get in there and figure it out by itself."
Gemini is introducing task automation features that enable the AI assistant to independently complete real-world tasks such as hailing Uber rides or placing DoorDash orders. Users provide a simple prompt, and Gemini launches the relevant app in a virtual window, navigating through steps automatically while allowing users to monitor, intervene, or let it run in the background. The system alerts users when decisions are needed or items are unavailable. This capability represents Android's evolution toward functioning as an intelligence system rather than just an operating system. Task automation will extend beyond Gemini to Android's next major release, with developers able to expose actions through MCP or Android's app functions framework, while Gemini handles automation independently where these frameworks don't exist.
Read at The Verge
Unable to calculate read time
[
|
]