When it comes to performance optimization, monitoring, and observability, the stakes are changing. Instead of thinking about CPU, memory, or bandwidth, engineers are being asked to figure out cost based on Token usage and LLM call observability. The way that observabiity works and more importantly, what data matters, is fundamentally different in the world of AI.

How engineers look at an environments performance has always been the same (look at logs/traces/metrics) and same rules will apply in the world of agentic infrastructure except now, instead of looking at a standard environment or application, engineers will be combing body-based responses and LLM usage.

This session will showcase how to reinvent the way we look at performance optimization and observability within environments using kagent, an open-source tool designed to run AI Agents declaratively and natively on Kubernetes.