RAG pipelines are easy to prototype but difficult to scale in enterprise settings. Instead of jumping directly to complex agent architectures, we evolve systems incrementally. First, we focus on systematic evaluation and optimization of a single RAG instance. Then, we introduce domain-specific assistants to better cover enterprise knowledge. Finally, we design a semi-agentic orchestration layer that simplifies access to these assistants and improves usability. We illustrate the discussion with a few real-world examples and practical observations.

David currently serves as Head of Data Science and Cognitive AI at DSV, the world's leading freight forwarding logistics company. He leads global, cross-functional teams building advanced analytics and AI solutions that drive operational excellence and innovation at scale. He holds an M.Sc. in Computer Science and a Ph.D. in Business and Management and brings over 16 years of experience in Data Science and AI, specialized in Recommender Systems and Generative AI. His work spans logistics, travel, healthcare, finance, and tech across both startup and enterprise environments. As a passionate researcher, David has co-authored more than 20 peer-reviewed publications, holds a patent in RecSys, and regularly speaks at international conferences on applied AI and machine learning.