Google AI Studio adds real-time multiplayer game coding with Gemini 3.1 Pro
Google has launched a vibe coding feature in Google AI Studio that converts natural language descriptions into working applications using Gemini 3.1 Pro. The platform now supports real-time multiplayer games and automatically configures databases, authentication, and third-party service integrations through an "Antigravity Agent."
Google Adds Real-Time Multiplayer Game Coding to AI Studio
Google has expanded Google AI Studio with a new "vibe coding" feature that enables developers and non-programmers to build working applications directly in the browser using natural language descriptions. The feature leverages Gemini 3.1 Pro to convert user intent into functional code.
What's New
The updated platform now supports building real-time multiplayer applications, including multiplayer games. Users describe what they want to build in natural language, and Gemini 3.1 Pro handles the technical implementation.
Apps built in the platform can handle:
- Real-time multiplayer interactions
- Payment processing
- Data storage and databases
- User authentication and login systems
- Messaging functionality
Automated Infrastructure Setup
Google introduced an "Antigravity Agent" that automatically detects when an application requires infrastructure components and configures them without manual intervention. The agent:
- Detects database requirements and provisions Firebase databases
- Sets up login and authentication systems automatically
- Installs necessary web tools like Framer Motion and Shadcn on demand
- Integrates third-party services (payment providers, Google Maps, etc.) using API keys
Framework Support Expansion
The platform now supports three major web frameworks:
- React
- Angular
- Next.js (newly added)
Apps are built and run directly in the browser, eliminating local development setup requirements.
What This Means
Google is positioning AI Studio as a low-code platform that significantly lowers the barrier to entry for building complex applications. By automating infrastructure setup and supporting real-time multiplayer functionality, Google targets both professional developers seeking faster iteration and non-technical users wanting to prototype ideas quickly. The addition of Next.js support signals focus on production-ready applications rather than simple prototypes. This directly competes with platforms like Vercel's AI capabilities and positioned agents from competitors, though Google's integration with Firebase and first-party services provides differentiation.
Related Articles
Google Gemini task automation now works on phones, taking 9 minutes to order dinner
Google has launched task automation for Gemini on Pixel 10 Pro and Galaxy S26 Ultra, allowing the AI to autonomously use apps for food delivery and rideshare services. The feature works but is slow—taking approximately nine minutes to complete an order—and remains limited to a small beta subset of apps. Despite performance limitations, it represents the first practical demonstration of an AI assistant actually controlling a phone outside of controlled demos.
Google testing Gemini app for macOS with Desktop Intelligence feature
Google is testing a native Gemini app for macOS, according to Bloomberg. The app would compete directly with OpenAI's ChatGPT and Anthropic's Claude, both of which offer standalone Mac applications. A key differentiator is 'Desktop Intelligence,' which allows Gemini to view screen context and pull content from apps to personalize responses.
Google begins beta testing dedicated Gemini app for macOS
Google has begun beta testing a dedicated Gemini app for macOS with select users, according to Bloomberg. The early version includes only critical features and hints at a "Desktop Intelligence" capability that lets Gemini see screen context. The move addresses a competitive gap, as Anthropic and OpenAI already offer native Mac apps for Claude and ChatGPT.
Google expands Universal Commerce Protocol with cart, catalog, and loyalty features for AI agents
Google has expanded the Universal Commerce Protocol (UCP) with shopping cart, catalog, and identity features designed for AI agents. The new capabilities enable agents to add multiple items to carts, access real-time product data including prices and availability, and preserve shopper loyalty benefits across retailers.