August 2025
Beginner to advanced
3h 20m
English
conference
Infrastructure & Ops Superstream: AI-Driven Operations and Observability
by Sam Newman, Niall Richard Murphy, Abi Aryan, Austin Parker, Aman Khan, Dylan Patel, Milly Leadley
Closed Captioning available in German, English, Spanish, French, Italian, Japanese, Korean, Portuguese (Portugal, Brazil), Chinese (Simplified), Chinese (Traditional)
Overview
AI isn't just playing around the edges of IT; it's fundamentally reshaping how tech is built, run, and managed.
Host Sam Newman and industry experts share practical insights and actionable strategies to deal with the dual transformations triggered by AI: how it optimizes operations, and how infrastructure must evolve to truly harness its power. Our panel addresses AI-driven operations and observability (AIOps) to show how machine learning enhances traditional IT functions, including automating crucial tasks such as incident management and system performance monitoring. You’ll learn how AIOps empowers system reliability, platform, and DevOps teams to find root causes faster, reduce alert fatigue, and implement strong predictive maintenance. You'll also learn the infrastructure essential for AI itself, including the specialized systems needed to reliably power demanding AI and ML workloads, and explore how core principles of operating technology systems are vital for building and maintaining next-generation AI environments. These sessions will leave you better equipped to both optimize your tech operations with AI and confidently deploy it at scale, ultimately driving improved system reliability and efficiency across all your technology.
What you’ll learn and how you can apply it
- Gain a comprehensive understanding of the evolving landscape of AIOps, including the challenges and opportunities for infrastructure and operations to effectively support and manage AI workloads
- Learn practical methods for evaluating and improving LLM agents in AIOps using measurable, testable techniques
- Master strategies for comprehensive observability across the entire LLM pipeline, from logging to error tracking, to build resilient AI systems
- Discover advanced evaluation and monitoring stacks used by top AI teams to identify and prevent AI system failures
Recommended follow-up:
- Read Observability Engineering, second edition (early release book)
- Read LLMOps (book)
Please note that slides or supplemental materials are not available for download from this recording. Resources are only provided at the time of the live event.
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Watch now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.