As AI and automation reshape modern software, datasets themselves can become active, intelligent components in cloud-native systems. This session introduces Agentic Datasets - a Kubernetes-native pattern where datasets act as self-managing data products capable of reasoning, triggering workflows, and coordinating with AI models.

Each dataset runs as a DatasetAgent, defined as a Kubernetes Custom Resource (CRD) encapsulating metadata, logic, and declarative workflows packaged as OCI bundles. These workflows execute securely within the cluster as Pods or Jobs, performing automated tasks such as validation, reindexing, or embedding generation - without external orchestration.

Attendees will learn how controllers, service meshes, and GitOps pipelines enable these agents to operate autonomously, and how LLM-powered reasoning enhances workflow decision-making. The talk concludes with a reference architecture and practical steps for deploying intelligent, AI-assisted data products on Kubernetes using open-source tools.