Keynote: AI Enabled Observability Explainers - We Actually Did Something With AI! - Vijay Samuel

Vijay Samuel

KubeCon + CloudNativeCon Europe 2025 · Keynote

In this insightful KubeCon EU keynote, Vijay Samuel, a Principal MTS Architect in reliability engineering at eBay, unveiled a pragmatic approach to integrating Artificial Intelligence into the complex world of observability. Titled "AI Enabled Observability Explainers - We Actually Did Something With AI!", Samuel's talk addressed the escalating challenges of managing highly distributed systems at massive scale, where traditional manual triage and even early machine learning models fall short. The core thesis revolves around the strategic combination of advanced engineering techniques with the capabilities of Large Language Models (LLMs) to create deterministic, high-quality "explainers" that significantly reduce the time and effort required for incident response.

AI review

Samuel's keynote from eBay delivers a refreshingly honest and technically grounded take on integrating AI into observability. Moving beyond the 'silver bullet' hype, he details a pragmatic, engineering-first approach to building deterministic 'explainers' using LLMs. This talk provides concrete, actionable strategies for leveraging AI's strengths in summarization and simple reasoning, while mitigating its inherent weaknesses through rigorous data preparation and API-backed components. It's a valuable blueprint for anyone serious about improving incident response in complex distributed…

Watch on YouTube