Agentic Workflows - How Salesforce Manages 1000+ Clusters

Explore a conference talk from AWS re:Invent 2025 that reveals how Salesforce revolutionized Kubernetes cluster management at massive scale using generative AI and multi-agent collaboration. Discover the groundbreaking approach that enables platform teams to overcome the escalating challenges of managing multi-tenant Kubernetes environments as they grow increasingly complex. Learn how intelligent agents create self-healing, automated cluster management systems that dramatically reduce both mean time to identify (MTTI) and mean time to resolve (MTTR) issues across enterprise-scale deployments. Examine real-world implementation strategies and practical insights from Salesforce's experience managing and troubleshooting over 1,000 Kubernetes clusters through agentic workflows. Gain understanding of how multi-agent collaboration transforms traditional cluster operations, enabling more efficient resource management and automated problem resolution in large-scale cloud environments. Understand the technical architecture and methodologies behind intelligent cluster management systems that leverage AI to anticipate, detect, and resolve operational challenges before they impact business operations.