At its "Android Show: I/O Edition" event on Tuesday, Google unveiled a suite of new AI features under its Gemini Intelligence branding. These capabilities enable the AI to perform tasks across different apps, browse the internet, fill out forms, transcribe speech, and even let you "vibe-code" your own Android widgets.

Google had already introduced some agentic features to Gemini earlier this year at the Samsung Galaxy S26 launch, such as ordering food or booking a ride. At that time, the company announced Gemini would soon handle more complex tasks, like reserving a front-row bike for a spin class, locating a course syllabus in Gmail, and searching for related books.

Now, Google’s AI assistant can manage a multistep process, such as copying a grocery list from your notes app and then adding items to your shopping cart. To use this, you press the phone’s power button and describe the task, with the screen’s current content serving as context. Google noted that Gemini will wait for your final confirmation before completing the checkout.

Additionally, a feature first introduced in January, which let Gemini browse the web for you and complete tasks like booking an appointment as part of an experimental rollout, is now coming to Android. In late June, Android devices will also get Gemini in Chrome, an AI feature that helps summarize web content or answer questions about a webpage, similar to the desktop version. Another useful addition is Gemini’s ability to fill out forms after learning details about you through Personal Intelligence—a feature that is opt-in and can be turned off in settings at any time.

Plus, Gemini is coming to Android’s Gboard keyboard. Google is leveraging Gemini’s multimodal capabilities with a new feature called Rambler in Gboard, which functions like other AI-powered dictation apps. It allows you to speak in your own tone, transcribe the speech, and format it by removing filler words.

### Vibe code your own Android widgets Vibe coding apps are gaining momentum, and Google wants to give Android users a taste of this trend. The company is introducing a way for users to build Android widgets simply by describing them in natural language. For instance, you could create a meal planning widget with a query like, "Suggest three high-protein meal prep recipes every week."

The concept of creating a widget isn’t entirely new to Gemini. Notably, hardware startup Nothing released a similar tool last year. Google said that Gemini Intelligence will follow the company’s Material 3 expressive design language in its features. These AI-powered features will first roll out to the latest Samsung Galaxy and Google Pixel devices this summer, with availability across other Android devices later this year.