Enterprise AgentOps with Red Hat AI Enterprise

Join this hands-on technical workshop to experience how Red Hat AI Enterprise helps organisations move AI initiatives from experimentation to secure, scalable production.

You will gain practical experience building, deploying and operating enterprise-grade AI solutions using a flexible model strategy that combines self-hosted models with Models as a Service (MaaS).

In this workshop, you will:

• Deploy and consume enterprise LLMs – Experience running self-hosted models on Red Hat AI and accessing centrally managed models through Models as a Service
• Monitor AI workloads in production – Use Red Hat AI's integrated observability capabilities to track key metrics and logs across your AI applications
• Trace multi-agent executions – Follow requests through multi-agent frameworks and Model Context Protocol (MCP) tools to understand complete execution and decision-making paths
• Evaluate LLM quality at scale – Combine distributed tracing with LLM evaluations in MLflow to measure and maintain the quality of agent and model outputs
• Automate AI deployment pipelines – Move from manual notebook-based evaluations to continuous, automated AI pipelines running on the platform

Recommended Prework:

To get the most out of this session, we recommend reviewing: ​

• Red Hat AI Foundations Technologist Course: Explore Learning Path ​
• Introduction to Machine Learning with Jupyter Notebooks: Read Article

Who should attend:

• Data Scientists, AI Engineers and Application Developers
• Application architects, Enterprise architects
• IT decision makers, IT directors