Learning Objectives

  • Manually instrument LLM operations using workflow, embedding, retrieval, task, and tool spans
  • Capture contextual data with annotations to provide visibility into complex chains
  • Analyze execution flow and operation relationships using flame graphs and span lists
  • Identify and debug retrieval failures that lead to inaccurate responses

Primary Audience

This course is designed for engineers who have completed Getting Started with LLM Observability and want to build observability into their AI applications. Software developers, AI engineers, and DevOps teams will benefit from this course.

Prerequisites

Recommended: Getting Started with LLM Observability

Technical Requirements

In order to complete the course, you will need the following:

- Chrome or Firefox

- Third-party cookies must be enabled to access labs

Course Navigation

At the bottom of each lesson, click MARK LESSON COMPLETE AND CONTINUE button so that you are marked complete for each lesson and can receive the certificate at the end of the course.

Course Enrollment Period

Please note that your enrollment in this course ends after 30 days. You can re-enroll at any time and pick up where you left off.

Course curriculum

    1. Welcome to Tracing LLM Applications

    1. Instrumenting spans

    2. Visualizing traces and spans

    3. Lab: Trace every step in LLM workflows

    1. Summary

    2. Feedback Survey

Tracing LLM Applications

  • 1 hours to complete
  • Beginner
Enroll for free