Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore how open source technologies can streamline the design and delivery of secure, scalable, and reproducible agentic AI systems in this 44-minute conference talk from the Linux Foundation. Follow an end-to-end user journey that begins with secure container-based local experimentation using Podman Desktop, advances through modular multi-agent RAG workflows, and culminates in OCI-compliant model packaging and Kubernetes-native deployment. Discover practical strategies for integrating model governance via the LF AI & Data Model Openness Framework while achieving robust supply chain security and enabling observability across the AI lifecycle. Learn how open source tools like RamaLama and Llama Stack address the increasing complexity in tooling, governance, and operational workflows that enterprise AI engineers face as AI evolves from isolated model development to system-level deployments. Gain insights into building internal AI platforms and modernizing MLOps practices, understanding how open tooling empowers teams to confidently operationalize next-generation AI systems at enterprise scale.
