CNCF On-Demand: Autonomous Agents on K8s – Durable Execution for AI
Kubernetes Ai agents Autonomous agents Durable execution Cloud Native Cncf Agentic ai Kubernetes operators Mlops Production ai Agent recovery Harness pattern
This session teaches developers how to run autonomous AI agents reliably on Kubernetes using the harness pattern and durable-execution primitives. It covers practical implementation of pod restart handling, mid-execution recovery, and asynchronous human-in-the-loop checkpoints for production AI systems. Ideal for platform engineers and ML Ops developers building agentic AI systems in cloud-native environments.
Related videos
Keynote: The Future of Cloud Native Is… Agentic - Lin Sun, Head of Open Source, Solo.io (ASL)
Keynote: From Inference to Agents: Where Open Source AI Is Headed - Panel (ASL)
MCP support in Envoy - Boteng Yao, Google, Software Engineer
Poison Control: Unifying Software and Content... Anmol Krishan Sachdeva & Ankit Kotnala, Google
Policy-as-Code for LLM Inference: Cost & Security Guardrails - Sakalya Deshpande, SAP Labs
Best of KubeCon + CloudNativeCon Amsterdam 2026
Beyond Dashboards: Cultivating the Observability Mindset - O. Hope Amaechi-Okorie, JSON Schema
Evolving KServe: The Unified Model Inference Platform for Both Predictive and... F. Spolti & J. Lee
Sponsored Keynote: Scaling Platform Ops with AI Agents: Troubleshootin... J. Palma & N. Yellin (ASL)
Keynote: Rules of the Road for Shared GPUs: AI Inference Scheduling at Wa... M. Muralikrishnan (ASL)
Cloud Native Live: Kubernetes v1.36 Release
