Google AI Studio now builds full-stack Kotlin Android apps and publishes them to Google Play
Google AI Studio, with Gemini 4 Carbon and Hydrogen, can now take a prompt to a Kotlin Android app with Cloud Firestore persistence, Google Sign-In and Gemini API calls, then publish it to a personal Google Play library. The features began rolling out on November 17, 2026.
Google AI Studio can now generate full-stack Kotlin Android apps, including a Firebase backend, and publish them to Google Play, Google announced on November 17, 2026. Google says the Build agent, working with Gemini 4 Carbon and Hydrogen, takes a single prompt to a production-ready app with data persistence, user sign-in and AI features. All of the features are rolling out today.
What launched
According to Google, previously generated Android apps in AI Studio were limited to local session storage. The Build agent now detects when a prompt needs persistent storage, sign-in or generative AI features, and with the developer's confirmation provisions the backend and wires up the Kotlin codebase.
- Cloud Firestore: The agent provisions a database, configures the Firebase Android SDKs and generates Firebase Security Rules tailored to the data model. Google says data syncs across sessions and devices, with offline caching that syncs when connectivity returns.
- Firebase Authentication: The agent configures Google Sign-In and per-user authorization rules so users can only read and write their own documents.
- Firebase AI Logic and App Check: When an app calls Gemini models, the agent configures Firebase AI Logic so API keys are not hardcoded in the APK. It enforces Firebase App Check using Google Fraud Defense (formerly reCAPTCHA Enterprise), which verifies that requests come from an authentic, untampered app, both in the browser emulator and on Google Play.
The agent also adds the Firebase Bill of Materials (BoM). Google's sample output is a WorkoutRepository class that calls the gemini-4-hydrogen model through Firebase AI Logic and writes results to a Firestore workouts collection.
Emulator and agent workflow changes
- Faster startup and 1200p HD streaming: Emulators boot with lower latency, and an HD toggle in the toolbar switches the stream to 1200p.
- Real-time audio output: Audio from the Android emulator plays in the browser, which Google says allows testing of Gemini Live API voice companions, text-to-speech coaches, games and media apps.
- One-click screenshot to agent: A "Take a screenshot" button captures the live app screen and attaches it to a prompt so Gemini can update Kotlin UI code with visual context.
- Custom fonts: The agent downloads, configures and applies requested typography across the Jetpack Compose theme.
- Android CLI: The Build agent now uses the official Android CLI to scaffold projects, query current Android documentation and run Gradle builds. Google says this reduces build errors and supports more complex multi-screen architectures.
Publishing to Google Play
A Play account can be set up in a few clicks from the publish panel, using a standard Google account. AI Studio builds and signs the Android App Bundle (.aab) and publishes it to the developer's personal Google Play library, from which the app can be installed on a phone. Google says building and testing on your own device from the Play Store is at no cost. Pricing for Gemini 4 Carbon and Hydrogen, context window sizes and benchmark scores were not part of this announcement.
To start, open Google AI Studio Build and select the Android chip at the top of the workspace. The post is written by Mike Taylor-Cai, Product Manager, Google AI Studio.
What this means
The change moves AI Studio's Android output from local-only prototypes to apps with a cloud backend, authentication and a distribution path. The API key handling addresses a risk Google itself names: credential extraction from client APKs. By routing Gemini calls through Firebase AI Logic with App Check, the generated code avoids shipping keys in the app.
The publishing flow also replaces steps Google lists as historically required: enabling USB debugging cables, managing signing keystores locally or setting up a full developer console account. Whether apps generated this way meet production needs beyond personal Play library distribution is not addressed in Google's post.
Related Articles
Perplexity Brain Can Now Create and Update Agent Skills; 80,000+ Personal Skills Written for 20,000+ Users
Perplexity said on November 18, 2026, that Brain, the personalization system for its Computer agent, can now create and update reusable agent skills. According to the company, Brain wrote more than 80,000 personal skills for over 20,000 users between August 1, 2026, and November 14, 2026.
GitHub Copilot team customizations now generally available for organization teams
GitHub announced that team customizations for GitHub Copilot are generally available for organization teams. The feature lets teams share the Copilot plugins they rely on without asking every member to repeat the same setup.
Google releases Genie 4 to AI Ultra subscribers with real-time prompt editing and native audio
Google is rolling out Genie 4, which it calls its most realistic and interactive world model yet, to eligible Google AI Ultra subscribers in Project Genie. The update adds real-time native audio, mid-session text prompting, a world-building agent and a community gallery. Genie 3 also gains sessions of up to 3 minutes.
Google adds "temporary threads" to AI Mode in Search, detaching chats from your account
Google is adding "temporary threads" to AI Mode in Search, a chat option that detaches the session from the user's account. The conversations won't resurface in search history or recommendations. The feature is rolling out globally on desktop and mobile across all supported languages.
Comments
Loading...