Keynote: Into the Black Box: Observability in the Age of LLMs - Christine Yen
Christine Yen
KubeCon + CloudNativeCon Europe 2025 · Keynote
In this KubeCon EU keynote, Christine Yen, co-founder and CEO of Honeycomb, addresses a critical challenge facing modern software development: how to maintain reliability and debug systems built with **Large Language Models (LLMs)**. As LLMs become ubiquitous, offering "magical" capabilities through cheap API calls to foundation models, they introduce a new layer of complexity and unpredictability that traditional software development practices are ill-equipped to handle. Yen argues that the very nature of LLMs – their nondeterminism, black-box operation, and unbounded input variations – renders conventional testing, mocking, and debugging strategies largely ineffective.
AI review
Christine Yen's keynote cuts through the LLM hype to address a fundamental and pressing challenge: how to build reliable systems with inherently unpredictable components. She makes a compelling, technically sound argument for observability as the only viable paradigm, extending well-understood principles (traces, spans, high-cardinality data) to this new domain. The integration of evals into a continuous feedback loop driven by production observation is a critical insight. This isn't just theory; it's a practical, actionable blueprint for any engineer or architect grappling with generative…