Welcome to the Accelerate AI with Cloud Run workshop!

NOTE: This is a Google-led event and any questions should be directed to the team’s alias listed on the RSVP page for attention.

This is a hands-on program designed to take your AI applications from prototype to full-scale production. In the world of AI development, a great idea is just the beginning. The real challenge lies in transforming that initial spark into a secure, scalable, and robust application that can handle real-world demands.

Get ready to get your hands dirty! This is an interactive session, not a lecture. Through a series of live labs, you'll tackle real-world challenges, from securing your services to deploying advanced AI agents. You will leave with practical skills and the confidence to take your own AI projects to the next level.

Note: To join the workshop, you must bring your own laptop and power cable. The activities are intended for laptops and cannot be completed on a tablet or phone.

Who Should Attend?

This hands-on workshop is designed for software developers, data scientists, and AI practitioners who have some experience building applications or working with models, and are looking to productionize them. To get the most out of the labs, you should have foundational knowledge of a programming language like Python and be comfortable using the command-line interface. While expertise is not required, a basic understanding of Cloud computing concepts, web APIs, and containerization technology will be highly beneficial.

What You Will Learn:

• Deploy Secure, Production-Ready Services: Master the essentials of securing your applications on Cloud Run. You will build and deploy a Model Context Protocol (MCP) server and learn to implement authentication to ensure that only authorized clients and agents can interact with your service.
• Build Intelligent Agents: Dive into the Agent Development Kit (ADK) to construct an intelligent agent capable of understanding a goal and using tools to achieve it. You'll connect your agent to the secure MCP server you built, giving it the power to perform real-world tasks.
• Containerize and Deploy: Take your working agent and prepare it for a consistent, portable deployment. This is a crucial step for managing applications in a serverless environment.
• Harness the Power of GPUs on Cloud Run: Deploy your containerized agent to a Cloud Run instance and attach a GPU to accelerate your models. You will gain hands-on experience managing production configurations and testing a live, GPU-accelerated application.