Every organization is building a strategy to build and deploy around AI, with many leveraging the power of Kubernetes and containers to underpin their AI stack. Join this session to find out how to quickly and easily integrate Open and Proprietary AI Models into your Developer workflow on Kubernetes to speed innovation while maintaining secure and available data. In this session, we explore the use of chatbots, retrieval augmented generation (RAG), and iteration for inference experimentation without delay, and look at the best practices for building, running, and deploying these applications on Kubernetes.