This session is designed for platform engineers, DevOps practitioners, and cloud architects looking to run AI agents reliably in production. Participants will learn how to design and deploy multi-agent AI systems on Kubernetes, using familiar cloud-native building blocks. We’ll walk through the agent stack—LLM-powered agents, tools, memory, and coordination—and show how Kubernetes enables scalability, resilience, security, and observability. Through real-world patterns and architectural examples, attendees will gain practical insights into engineering AI-native platforms that move beyond experimentation to production-ready autonomous systems.