Google launches Playground platform for creating games with AI

Google has unveiled Playground, an experimental AI-powered platform that lets users create simple games using ordinary text prompts. No programming skills are required to use the service: beginners will be provided with a step-by-step guide to help them get started with “developing” their first game.

Google promises full creative control: users describe an idea and can then change the rules, physics, characters, and environment by entering commands in the chat.

All games are created and run in the browser, with support for both computers and mobile devices. Users can start a game from scratch or use templates. Once created, a project will be available for testing in the browser, and the finished game can be kept private, shared with friends via a link, or published in the Playground Explore gallery so that players around the world can test it. Some genres offer leaderboards and multiplayer modes. Users will be able to follow the creators of the best games to keep track of new releases.

Playground is powered by Google’s Gemini, Nano Banana, and Lyria models, enhanced by a specialized game-generation system. The service itself is free, but Google One subscribers receive higher weekly token limits. In the future, Playground will be integrated with the Unity Spark platform, allowing users to transfer their projects to the Unity environment and use more sophisticated game mechanics and 3D graphics.

At launch, the Playground platform is already available to users over the age of 18 in the US.