From Data to Decisions: A Domain-Driven Path to Industrial AI

English
This talk will be held in English. / Dieser Vortrag wird auf Englisch gehalten.

Artificial Intelligence used in the real industry often faces a fundamental gap when data scientists create shiny models in a laboratory setting. Still, domain experts and operators need a system they can trust and rely on in production.

In this session, it is explored how Domain-Driven Design can be applied to design robust and interpretable AI architectures for complex industrial use cases.

Based on a real-world case study it is demonstrated how bounded contexts, ubiquitous language, and domain events transform the AI pipeline into a production system that communicates in the same language as domain specialists and quality managers.

Be familiar with the DDD and Architecture principles

Attendees see how the DDD principles create a solid architecture, spanning from image acquisition to defect detection, handling root causes, and generating reports that provide traceability, clarity, and a clear linkage between each stage and business goals, such as quality, safety, and cost reduction
Nikita Golovko Nikita Golovko is a seasoned Solution Architect with over 16 years of experience in designing scalable, secure, and cost-effective software architectures for industrial and business-critical systems. With a strong academic background and research in machine learning, Dr. Golovko bridges the gap between advanced AI technologies and real-world applications on the shop floor.