Monitoring traditional microservices is a solved problem. We know how to track CPU, memory, and latency. But how do you monitor the "reasoning" of an AI agent? If you can't measure the cost and logic of your GenAI workflows, you are flying blind in production.

This session explores how to adapt the open-source monitoring tools you already use (like Prometheus and OpenTelemetry) to track the health, infrastructure costs, and hallucination rates of agentic workflows. We will treat LLM calls just like any other microservice dependency, demonstrating how to instrument an AI pipeline, map token usage directly to infrastructure spend, and build dashboards that expose both system health and AI accuracy in real-time. Stop guessing what your agents are doing and start monitoring them like proper engineering assets.