July 24, 2025 - 11:00 AM EST

How to bring observability to LLM workflows—the next frontier in AI ops

Complete the form below to join this webinar

Large Language Models (LLMs) are rapidly reshaping how companies build AI-driven products, with organizations across every industry integrating LLMs into their workflows. But as adoption accelerates, a critical challenge has emerged: how do you gain visibility into what these models are actually doing in production?

Join AWS and Lumigo as we explore the growing need for LLM observability, from tracking prompt inputs and responses to debugging failures and monitoring performance across chains and agents. We’ll explore the most common observability needs teams face when deploying LLM-based workflows and discuss why traditional tools fall short.

You'll discover how Lumigo, an AI-powered observability platform originally designed for distributed cloud applications, has evolved for monitoring LLM workflows. Its native full-payload data capture capabilities make it uniquely suited to track complete prompt-response cycles, giving you deep insight into your AI applications. We’ll wrap up with a live demo showing how you can gain end-to-end visibility into your LLM pipelines in minutes.

What you’ll learn:

  • Why traditional observability tools fail with LLM workflows
  • What to monitor: prompts, responses, errors, and agent chains
  • How to debug and trace failures across your LLM pipeline
  • Where full payload data helps you gain complete end-to-end visibility into your pipeline
Meet your hosts:
orr weinstein
Orr Weinstein
Orr is VP of Product at Lumigo and has been building products for nearly two decades in various dev and product roles. Orr has formerly held leading Product roles at AWS, GCP, and Spot.io and was lead developer at the IDF and RAM Engineering. Orr holds a Master of Business Administration (M.B.A.) from The University of Chicago Booth School of Business and a Bachelor's Degree in Economics and Management from The Open University of Israel.
danilo
Danilo Poccia
Danilo works with startups and companies of any size to support their innovation. In his role as Chief Evangelist (EMEA) at Amazon Web Services, he leverages his experience to help people bring their ideas to life, focusing on serverless architectures and event-driven programming, and on the technical and business impact of machine learning and edge computing. He is the author of AWS Lambda in Action from Manning.

Complete the form below to join this webinar