The AI coding boom has come directly to Android app development. Google on Tuesday announced new native Android app creation capabilities in the web-based Google AI Studio, cutting the weeks-long setup and coding process to minutes.
The company also said that consumers will now be able to use Gemini AI to find the apps they want on both the Play Store and the web, expanding opportunities for developers to get their apps discovered.
Google says this new feature could be meaningful to everyone, from seasoned developers to first-time creators who want to quickly prototype new apps.
By offering the ability to essentially vibecode Android apps through a web-based tool, Google is increasing competition from other AI-powered development tools like Cursor, Replit, Lovable, and Claude Code, while also opening up Android development to a new type of user: non-technical creators. The news also represents an expansion of Google’s previous addition of AI-powered coding with Gemini to the desktop version of Android Studio.
The company says the app is built in the Kotlin programming language using Google’s Jetpack Compose toolkit and supports integration with hardware sensors such as GPS, Bluetooth, and NFC. However, the work created is for now only for personal use, as we plan to publish it for family and friends.
The company suggests that the technology could be used to create personal utilities, simple social apps, hardware-enabled experiences, or AI-powered experiences.
Currently, aspiring app developers can use the embedded Android emulator directly in a web browser to preview and interact with the apps they are building. Users can use the integrated Android Debug Bridge (adb) to install apps on their Android smartphones via a USB cable connected to their computer.
If you want to take your project further, AI Studio can automatically create an app record, package the bundle, and upload it to the Google Play Console’s internal test track for developers. This allows users to keep iterating on your app while updating their devices along the way.
If you want to take the next step to make your app more publicly available, you can hand off this version of your project to Android Studio by downloading the zip file and exporting it directly to GitHub. Google will eventually allow creators to publish their apps for use by family and friends, and will also add support for Firebase integration (Firestore, Firebase Auth, Firebase App Check, and other tools).
In doing so, the company envisions an ecosystem of Android apps where users can discover apps not only from the Play Store, but also among their network of friends.
However, in the latter case, Google is incorporating AI into the experience here as well.
A new AI-powered Ask Play overlay lets users discover new apps by having natural conversations with AI within the Play Store.
Perhaps more importantly, apps will start appearing through user conversations with Google’s Gemini virtual assistant, exposing developers’ apps to millions of users. This will be rolled out across Gemini on the web and Android in the coming weeks. Later this year, Gemini will show you more than 450,000 movies and TV shows, plus live sports streaming destinations. This allows users to link directly from their queries to the developer’s Android app containing the content in question.
Google previewed a slew of Android-related announcements last week, but held back from sharing any native Android app development news until the start of its annual developer conference, Google I/O, on Tuesday. This, along with the larger theme of this year’s event that spread AI across Google’s products, from workspace productivity apps to AI tools, search, mobile apps, and more, suggests that the company believes this is bigger news and more closely tied to its ideas for leveraging AI in the real world.
If you buy through links in our articles, we may earn a small commission. This does not affect editorial independence.
