Securing the Chain of Trust: A Hands-On Lab for Multi-Agent Systems on Cloud Run

Roll up your sleeves and code along with us in real-time to construct a layered security strategy for multi-agent applications on Google Cloud Run. In this hands-on lab, you will learn how to build a secure perimeter to control exactly what traffic gets in and out with VPC rules, configure least-privilege permissions so your agents only talk to what they're supposed to with IAM service accounts, and implement input validation to harden AI agent tool calls. You'll leave this session with a practical framework for securing your own generative AI applications immediately.