Inside the AI Team Weekly: AI Observability workflows and Prometheus exemplars (May 19th, 2026)

Grafana's AI team demonstrates new AI Observability features including instrumenting and visualizing agent workflows built with LangGraph to track each step, LLM calls, cost, and state. The video shows how to use Prometheus exemplars to attach trace IDs to metrics like time to first token, enabling engineers to jump directly from a latency spike to the specific conversation that caused it. Target audience is DevOps engineers and ML practitioners using Grafana Cloud who need to monitor and debug AI agent systems.