Aug 10, 2026
Melliyal Annamalai explains why knowledge graphs are becoming a
critical foundation for modern AI by providing the context that
helps AI agents deliver more accurate and trustworthy results. The
conversation explores how property graphs, RDF graphs, vectors, and
graph analytics work together to strengthen enterprise AI
applications.
In this episode of Digital Impact Radio Series
9, Franco Ucci speaks with
Melliyal Annamalai about the growing importance of
knowledge graphs in the era of artificial intelligence. As AI
systems become more capable, the discussion explores why knowledge
graphs are moving beyond their traditional role in analytics to
become an essential source of context for AI agents, retrieval
systems, and enterprise applications.
Melliyal explains the differences between property graphs and RDF
graphs, also known as semantic or knowledge graphs, and describes
how each graph model supports different use cases. The conversation
examines how knowledge graphs capture business concepts,
relationships, and domain expertise in a structured,
standards-based way that helps AI systems produce more precise,
explainable, and trustworthy outcomes. Real-world examples from
fraud detection, financial services, supply chain analysis, and
enterprise metadata illustrate how graph technologies continue to
evolve alongside AI.
Franco and Melliyal also discuss how vectors and graphs complement
one another, combining semantic similarity with explicit
relationships to provide richer context for AI. The episode
concludes with practical insights into industry ontologies, graph
standards, Oracle Graph, and the growing ecosystem of tools and
learning resources that are making knowledge graphs increasingly
accessible for enterprise AI solutions.