Cloud AI isn't always the best place to begin. With Foundry Local, developers can build, test, and optimize AI applications entirely on their own devices before seamlessly moving to Microsoft Foundry when it's time to scale. In this demo-driven session, we will guide you through installing and configuring Foundry Local, discovering and managing local AI models, and building applications that can switch effortlessly between local and cloud-based models. You'll also learn how technologies such as GPU acceleration and ONNX optimization can significantly improve performance and efficiency for local AI workloads. Whether you're exploring generative AI for the first time or building enterprise-grade solutions, this session will provide practical insights, real-world demonstrations, and proven best practices to help you confidently start developing AI applications locally—and prepare them for the cloud when the time is right.