Google launched Playground on Wednesday, Oct. 7, a web-based platform where anyone in the United States can describe a video game in plain language and get a playable version back without writing code. Users then refine the result by chatting—asking for different physics, rules, characters, or settings—and can share their creations with a link, according to Google's announcement.

"Today, we're introducing Playground, an experimental gaming platform that lets you create, play, and share custom games," Google wrote. "Playground lowers the barriers to creation, so bringing game ideas to life can now be as easy as describing it through a few prompts—no coding experience required."

The tool is live for U.S. users aged 18 and older, with tiered creation access rolling out based on each user's Google AI subscription. Google's announcement did not include prices or say which AI models power the tool, leaving both as open questions as the rollout widens. The company describes Playground as "an early experiment designed to make game creation more approachable."

Games built in Playground run in a web browser on phones and laptops. Creators can keep them private or publish them to a community gallery, where every game goes through a safety screening, and some genres support leaderboards and multiplayer.

Google leans into the language of vibe coding—an approach that builds software by describing it to an AI in natural language instead of writing code—with the pitch: "If you can think it, you can play it." Playground, however, appears to go beyond the simple results possible in a typical Google Gemini session, and it seems capable of using some of the same tools and resources that experienced game makers rely on in their daily jobs.

The upgrade path runs through Unity Spark, which Playground will soon integrate for creators who want professional-level mechanics and high-fidelity 3D graphics. In a joint release, Google and Unity said Spark arrives later this year, and Google says a closed beta is coming soon—two milestones that will show whether Playground can graduate from conversational prototyping to professional production work.

Unity builds the game engine, the software toolkit studios use to make games, and its then-CEO predicted in 2023 that generative AI would cut the time needed to build game worlds by five to ten times.

The launch follows earlier work by DeepMind, Google's AI research lab. In 2024, DeepMind unveiled Genie, a model trained on more than 200,000 hours of gameplay video that could turn an image or a text prompt into a simple 2D platformer. It had 11 billion parameters, the adjustable values where an AI stores what it has learned.

January, Google opened Project Genie to AI Ultra subscribers in the U.S., built on Genie 3, a so-called world model that generates an interactive world in real time as a user moves through it. Sessions were capped at 60 seconds, and Google warned that the generated worlds might not follow prompts or real-world physics. Read in sequence—2024 research demo, January subscriber preview, and now a web experiment open to U.S. adults—the releases trace text-to-game technology's path from lab curiosity toward consumer product.

That path is what unsettled markets earlier this year: game stocks sank the day after that January opening, with Unity closing down about 24% and Roblox and others also dropping, as investors worried AI could displace traditional game tools. Roblox, the platform where users build and play each other's games, had told investors in 2023 that it was moving toward letting anyone make avatars and clothing entirely through text prompts.

For someone who has never touched a code editor, Playground turns a game idea into a conversation rather than a career change—though only adults in the U.S. can try it for now. Anything generated this way will likely resemble a prototype before it resembles a hit; after all, Google itself says this is merely an experiment.