With the rapid adoption of AI models in software products, Chrome’s introduction of local-first, on-device AI models offers developers a powerful new way to build intelligent and fast AI features directly within the browser. This talk will explore Chrome’s Built-in AI models, their architecture, APIs, developer tooling, and also demonstrate how it supports low-latency AI experiences without relying solely on cloud-deployed models.

We’ll walk through the architecture behind Chrome’s on-device models, discuss real-world edge cases and common concerns from integrating the built-in AI APIs, and outline key system and compatibility requirements that every developer should know. This talk will also mention the evolution of Chrome’s AI ecosystem, from its early releases to current capabilities, along with a preview of upcoming features and insights from its developer community.

For advanced listeners in the audience, this talk will include Chrome’s hybrid AI support pairing with Firebase to extend applications with cloud-backed storage and processing, enabling developers to blend on-device intelligence with online workflows.

To keep this talk interactive and practical, I will use my open-source Chrome extension project built during the recently concluded Chrome AI hackathon as a demo, highlighting how the Prompt and Summariser APIs are being used in the Chrome extension.

In real life: the feature is urgent, the code is complex, and we at least need to keep things consistent, right? So, how do you stick to "good practices" -- in practice?

Well, sorting out your code is a bit like sorting out your life. If you shift your perspective, solutions tend to reveal themselves. I will show 20 real examples of React hooks, component compositions, types and interfaces "before and after" a Zen change. You will learn the 3 questions to ask when reading code that reveal how to reduce complexity, ease confusion, and relieve suffering.