About this talk

When base models and prompting aren't enough, AI agents need specialization. This talk dives into the two key strategies: RAG and Fine-tuning. RAG (Retrieval-Augmented Generation) uses vector search to give agents access to dynamic, external knowledge (like company docs) without changing the model. Fine-tuning "bakes" static knowledge into the model, changing its core behavior or style (like tone). The central question is: RAG or Fine-tuning? We'll provide a clear decision framework for when to use RAG, when to use Fine-tuning, and when to combine both. Attendees get a practical guide to choos