Nicole Koenigstein
Nicole Koenigstein is an AI Researcher and Practitioner in Agentic Systems, working across research, consulting, teaching, and direct system implementation to build reliable, production-ready AI systems. Her work focuses on multi-agent architectures, evaluation, safety, and long-term system behavior.
She served as an external evaluator for a European Commission AI Grand Challenge and has advised IOSCO on generative AI in regulated environments. She also serves on advisory boards for leading AI and quantitative finance conferences. Nicole regularly delivers invited talks and technical workshops across academia, industry, and international events.
She is the author of Math for Machine Learning and Transformers in Action with Manning Publications. Her book Transformers: The Definitive Guide: Applications Beyond NLP has been published by O’Reilly Media, and her forthcoming book AI Agents: The Definitive Guide will also be published by O’Reilly Media.
Session
AI agents are easy to demonstrate, but much harder to operate reliably in real products. Most agent content focuses on impressive prototypes, while the difficult questions begin when agents interact with users, tools, memory, external systems, infrastructure, and production constraints.
This full day masterclass focuses on the gap between agent demos and production ready agent systems. We will examine what breaks when agents move into real environments, what needs structure, what needs governance, what needs evaluation, what needs observability, and what needs serious engineering craftsmanship before agents should be shipped in real products.
Participants will learn how to reason about agent architectures, tool use, planning, orchestration, failure modes, monitoring, evaluation, security, and operational risk. The focus is not only on what agents can do, but on how to design systems that remain understandable, testable, observable, and controllable when agentic workflows become more complex.
The workshop is designed for engineers, architects, technical leads, AI practitioners, and decision makers who want to move beyond simple agent demos and understand what it takes to build agent systems that can survive contact with real users, real tools, real infrastructure, and real production environments.