Session details

Dive into building the next generation of Flutter apps featuring Offline AI Agents. This talk explores how to leverage the power of Edge AI and on-device processing to create intelligent agents that operate entirely without an internet connection, enhancing privacy, reducing latency, and enabling new functionalities independent of the cloud. We'll focus on using lightweight, state-of-the-art open models, particularly Google's Gemma family (including potentially upcoming versions like Gemma 3), which are designed to run efficiently directly on mobile devices. Discover how these models form the "brain" of our offline agents. A key part of this session will introduce a Flutter plugin (developed by the speaker) designed to seamlessly integrate models like Gemma, making it significantly easier to build these offline AI capabilities into your Flutter projects. Learn the practical steps to implement these agents: from selecting appropriate on-device model variants (like the latest Gemma models, or popular alternatives such as Deepseek and Mistral Small) based on task requirements, to integrating them using the Flutter plugin. Crucially, we will discuss the trade-offs involved – weighing the benefits of Edge AI (offline access, privacy, low latency) against the challenges (model size constraints, device performance) compared to traditional cloud-based AI solutions. We will explore techniques for structuring agent tasks and touch upon fine-tuning methods to tailor model behavior for specific offline functionalities. Furthermore, we'll delve into advanced capabilities like on-device Retrieval-Augmented Generation (RAG), enabling your agents to query and utilize local data sources (like notes or databases on the device) for highly relevant, context-aware interactions, entirely offline.