Asimov's Zeroth Law of Robotics: Observability for AI - Nicole van der Hoeven, Grafana Labs
Nicole van der Hoeven, Grafana Labs
KubeCon + CloudNativeCon Europe 2025 · Session
In this insightful talk, "Asimov's Zeroth Law of Robotics: Observability for AI," Nicole van der Hoeven, a Senior Developer Advocate and performance engineer at Grafana Labs, explores the critical need for observability in modern Artificial Intelligence (AI) applications. Approaching the subject with a self-professed "deep skepticism and hope," van der Hoeven argues that just as Isaac Asimov's fictional robots often failed in unexpected ways despite their programming, today's AI systems can also malfunction or produce undesirable outputs without clear insight into their internal workings. Her proposed "Zeroth Law" for robotics—that robots must be observable—serves as the foundational premise for understanding and mitigating these risks.
AI review
This talk cuts through the AI hype with a brutally honest and practical approach to AI observability. Van der Hoeven correctly identifies the critical need for specialized telemetry beyond traditional monitoring, leveraging OpenTelemetry and OpenLit to capture LLM-specific data like token counts and model versions. The truly novel contribution is the systematic use of K6 for automated testing against AI-specific failure modes such as hallucination, toxicity, and role adherence, providing a genuinely actionable defensive strategy. It's a clear, well-demonstrated session that offers concrete…