A chatbot that only talks is a demo. A chatbot that can act inside your app is a product. In this station, participants connect Gemini to the starter app using function calling. You define a few app functions, describe them to the model, and let it decide when to call them based on what the user types. We’ll cover writing good function descriptions, handling the model’s arguments safely, and showing the user what the AI did. We’ll use a bring-your-own-key setup with a model selector, so nothing sensitive sits on a server.

What participants build: a small AI assistant inside the starter app that can call two or three of its functions from natural-language requests.

What they take home: a working function-calling loop they can copy into their own projects, plus a short list of guardrails (validation, confirmations, limits).

Prerequisites: basic React (JavaScript or TypeScript), and a free Gemini API key from Google AI Studio. No other stations needed.