AgentOps Observability with Red Hat AI

Welcome to the AgentOps Observability with Red Hat AI workshop!

What you’ll learn

In this workshop, you will:

  • Monitor the Stack: Utilize Red Hat AI’s out-of-the-box observability stack to track key metrics and logs of your Agentic App

  • Trace Multi-Agent Executions: Track requests across multi-agent frameworks and MCP tools to understand the complete decision-making path

  • LLM Evaluations: Combine tracing with LLM evaluations (Evals) in MLflow to ensure your agents maintain high-quality outputs

  • From Development to Production: Move from manual notebook evaluations to automated AI pipelines that run continuously on the platform

Who this is for

This workshop is designed for SREs, Platform Engineers, and AI Developers/Engineers who want to implement end-to-end observability for multi-agent AI systems. See the Workshop Overview for detailed prerequisites and target audience.

Workshop environment

You will work with a multi-agent mortgage lending application built with LangGraph and integrated with Model Context Protocol (MCP) tools.

You will have access to:

All environment details and credentials are available in the lab interface.

Estimated time

This workshop will take approximately 1 hour 30 minutes to complete. An abbreviated 45-minute path is also available, covering Modules 1, 3, and 4.

You can work at your own pace.

Let’s get started!

Click on Workshop Overview in the navigation to begin your learning journey.