A practical two day technical course for participants who are new to Arize Phoenix and want to trace, evaluate, analyse, and debug LLM applications. The agenda progresses from Phoenix architecture and AI tracing through RAG and agent observability, evaluations, datasets, experiments, and systematic failure analysis. The course focuses on using observability and evaluation together to identify problems, test improvements, and make evidence-based changes to AI applications.
You will learn how Phoenix captures and visualises traces from LLM applications using OpenTelemetry and OpenInference. You will analyse prompts, retrievals, model calls, tool use, latency, and application behaviour, then use evaluations and experiments to measure whether proposed changes improve quality. You will also learn practical debugging workflows for RAG systems and AI agents.
*We customize the course outline and content to your specific needs and relevant use cases.
Module 1: Arize Phoenix and AI observability fundamentals
Module 2: Instrumenting LLM applications
Module 3: Trace analysis and application debugging
Module 4: RAG and agent observability patterns
Module 5: Evaluation fundamentals with Phoenix
Module 6: Evaluating RAG systems and AI agents
Module 7: Datasets and experiment analysis
Module 8: Debugging and continuous AI improvement
Hands-on learning with expert instructors at your location for organizations.
Master new skills guided by experienced instructors from anywhere.