Have you ever tried building an AI agent, only to get bogged down in massive, complex frameworks just to get a basic output? If you want a clean, code-first way to build and debug agents without the boilerplate, Google’s open-source Agent Development Kit (ADK) is what you need. In this post, you will learn how to set up the Python SDK, code your first Gemini-powered agent that checks facts, and test it locally using ADK’s built-in web playground. Let's get started!

Google AI Studio has recently added an array of new features, calling it a new full-stack vibe-coding experience and vibe-coding-to-production. The new feature include ability to generate music, use Google Search data, use Google Maps data, add a database and auth, and add Gemini intelligence, to name a few. In this post, you will learn about adding a database and auth, which uses Google Firebase in the background to do so. Let’s get started!

You can run open models with other apps, such as Ollama. Docker Model Runner shines when you want to connect your application’s Docker container with an open model. It feels more native to Docker to define both the application and the model in a single Docker Compose file. You will learn to do so in this tutorial with a demo app built with Node.js that talks to Smollm2, defined in a Docker Compose file. Let’s get going!