Observability AI Agents – Behind the Scenes | Elastic and PagerDuty
Details
Join us for a meetup during the week of KubeCon Amsterdam, hosted together with PagerDuty.
Agenda:
17:45 Doors open, Walk-in and socialising
18:00 Opening
18:10 Observability AI Agents – Behind the Scenes (Elastic)
18:55 The State of AI in Incident Management
19:30 Food & Drinks
20:30 End
Talks:
Observability AI Agents – Behind the Scenes
In the age of AI, nearly every observability platform offers some form of intelligent assistance — from automated root cause analysis and incident triage to query generation and dashboard creation. Yet for most users, these AI agents remain black boxes: powerful, but opaque.
What principles guide their design? How do they reason over telemetry data? And what if you need to customize, extend, or build agents tailored to your organization’s workflows? In this talk, we’ll peel back the curtain on observability AI agents. We’ll explore the reasoning strategies, and orchestration tools that power them. Finally, we’ll dive into how Elastic’s AgentBuilder and Workflow ecosystem enable teams to move beyond out-of-the-box automation — empowering you to shape and build the agent experience your operations demand.
Speakers: Alexander Wert, Director, Software Engineering and Miguel Luna, Principal Product Manager (Elastic)
The State of AI in Incident Management
How many times were you woken up during the night to either spend more time than you would like trying to figure out what exactly broke, or just bash your keyboard in frustration once you figure out it was actually a false positive?
What if there was a better way? I mean, AI is everywhere nowadays. What if we used it to solve these problems?
Let's take a journey through the evolution of Incident Management until the birth of AIOps. There, let’s see where we succeeded, failed, and how these lessons should affect our future in a GenAI and Agentic Era.
In this new Era, how do Agents help us when incidents come to knock? Will they speed us up? Are they even able to fix incidents without waking us up?
If Agents are here to change everything, how do we avoid repeating the mistakes of the past? How do we successfully build a culture of adoption in our organization? Where are the gaps? And finally, can everything be “agentified”?
Speaker: Daniel Afonso. Sr. Developer Advocate (PagerDuty)
Make sure to find us at KubeCon and join one of these talks given by Elasticians:
- When OTTL goes off the rails: debugging transformations with confidence
- Enriching telemetry signals through lookups in the OTel collector
- Going global: lessons from internationalizing OpenTelemetry docs
- To upstream or not? Why becoming the maintainer of your dependencies matters
- The fourth pillar arrives: OpenTelemetry profiling alpha in action
- Semantics matter! Lessons from stabilizing OpenTelemetry's system conventions
Daniel Afonso is a Senior Developer Advocate at PagerDuty, SolidJS DX team member, Instructor at Egghead.io, and Author of State Management with React Query. Daniel has a full-stack background, having worked with different languages and frameworks on various projects from IoT to Fraud Detection. He is passionate about learning and teaching and has spoken at multiple conferences around the world about topics he loves. In his free time, when he's not learning new technologies or writing about them, he's probably reading comics or watching superhero movies and shows.