WebMCP and WebAI: Exploring native AI tools in Chrome
SessionTrack CEnglish
Artificial Intelligence is no longer exclusive to servers and cloud models, but has become a native part of the browser. At Google I/O 2025, Chrome presented a set of Web AI APIs that allow for text summarization, language detection, content translation, message rewriting, and much more—all directly in the browser, with support from the embedded Gemini Nano model. Furthermore, Chrome WebMCP was recently launched, providing a standard way to expose structured tools, ensuring that AI agents can perform actions on your website with greater speed, reliability, and accuracy.
In this talk, you will discover how these new APIs work, what problems they solve, and how they can transform the way we develop web applications. We will explore practical usage examples, compare local versus cloud execution, and understand the impacts on privacy, latency, cost, and user experience.
Get ready to experience the new era of the Web, where the browser is not just an intermediary, but also an intelligent agent that empowers your applications.
Kevin Uehara
Kevin Uehara is a Software Engineer at iFood and an active Google Developer Groups Campinas (GDG) collaborator. Recognized three times as a Microsoft MVP and Google Developer Expert (GDE) for his contributions to the tech community, Kevin is also the organizer of FrontIn Campinas, as well as an international and national speaker and tech content creator. Based in Brazil, he is passionate about sharing knowledge and inspiring other developers in the frontend ecosystem.