Session abstract
What you’ll learn
When AI agents have to execute complex, multi-hop reasoning across interconnected knowledge domains, traditional Retrieval-Augmented Generation (RAG) systems fail. Although vector-based retrieval is very good at finding content that is semantically similar, it cannot find meaningful connections between data, which leads to hallucinations. In this talk, we'll dive into how engineers can ground agents and large language models (LLMs) to uncover connections in data that are often missed by conventional RAG techniques.