Grab a refreshing slice of cold watermelon (because it’s summer in Tokyo and I love it!), and let me tell you a story about how a small team of us turned a wild idea into a living, breathing web game.

If you’ve spent any time in Google I/O over the last few years, you might remember Adventure—the virtual conference technology that powered major Google events during the pandemic. It was vast, beautifully illustrated, and collaborative. But it was also heavy, transient, and required an army of human moderators.

Gemma, a family of open models, are lightweight, remarkably capable, and have a wonderful “tunability” that makes them perfect for personal projects and enterprise-grade applications alike. But as the ecosystem grew, I found myself asking the same questions over and over:

• Which exact model size fits my constraint?
• How do I build an application powered by Gemma that does XYZ?
• How to deploy a Gemma model to production on Google Cloud for my team to use?

To solve this, we put together a living repository called gemma-skills (which we’re releasing!). It’s a curated, structured collection of developer skills designed to help both humans and agentic AI assistants build beautiful applications with Gemma models without the friction.

🐢 Speaking into Canvas

If you’re anything like me, your very first taste of “programming” might have involved a tiny triangle on a glowing CRT monitor. You typed FORWARD 100 and watched as the little turtle drew a line across the screen. It was pure magic. You were making the computer do things. (See also: Logo (programming language))

Recently, I rediscovered this magic with AI, a project called Turtle-Gemma, and it brings that exact childhood magic to the modern AI landscape.

💎 From Mining Ores to Mining Insights

Whether you are navigating the underground biomes of Core Keeper or the complex spreadsheets of a small business, “information overload” is the final boss.

A RAG (Retrieval-Augmented Generation) system is like giving an AI a specialized guidebook. Instead of relying on its general training, the AI looks at your specific data-like a game wiki, your research notes, or legal contracts-to give you pinpoint-accurate answers.

When catching up on Google’s AI news, you hear Gemini, and then you hear Gemma. The names are so similar-like twin siblings-that it’s easy to scratch your head and wonder, “What exactly is the difference?”

Technically speaking, Gemini is a family of multimodal generative AI models and intelligent assistants developed by Google DeepMind, while Gemma is a collection of lightweight open models built from the same technology that powers our Gemini models… but wait!