AI agents are changing how we build software. This video covers everything you need to know, from architecture to deployment on Cloud Run and Vertex AI. Ready to dive in and build the next big thing? Head to the codelab and get started. → AI agents are a new type of application architecture, relying on a language model to reason, remember, and plan complex tasks. This video provides a comprehensive guide to building and deploying them on Google Cloud, covering both the flexible and cost effective Cloud Run and the managed, end to end Vertex AI platform. You'll learn about key concepts like tool calling, model agnosticism, and the benefits of using frameworks like LangGraph and Google's open source Agent Development Kit (ADK). We'll also demonstrate how to use Cloud Run for a smooth ""source to URL"" deployment and explore the Vertex AI agent builder for an enterprise ready solution with built in observability and rich interaction capabilities. Speakers: Wietse Venema, Steren Giannini, Sita Lakshmi Sangameswaran Check out the cloud session track from Google I/O 2025 → Check out all of the sessions from Google I/O 2025→ Subscribe to Google Cloud Tech → Event: Google I/O 2025 Products Mentioned: Cloud, AI/Machine Learning