Biography
Dr. Jesús Barrasa is AI Field CTO at Neo4j, where he works with organisations combining large language models with knowledge graphs. He holds a PhD in Artificial Intelligence and Knowledge Representation, and brings over 20 years of experience across the data management space, split between industry and academic research. Before joining Neo4j in 2015, he worked at data integration companies including Denodo and Ontology Systems.
He co-authored the O'Reilly book "Building Knowledge Graphs: A Practitioner's Guide" and co-hosts the monthly webcast GoingMeta, which explores semantics, knowledge graphs, and AI. His work centres on a practical problem in enterprise AI: model quality isn't the bottleneck, meaning that stays implicit and fragmented across systems is. Making semantics explicit through ontologies and graph structures changes how AI systems get designed, built, and operated.
His perspective is especially relevant for audiences interested in GraphRAG, semantic layers, and moving GenAI projects from pilot into production.
Session
- AI FoundationsSpeaker
Use Case 2 - The Knowledge Layer: Thinner Agents on a Smarter Substrate
Tuesday 22 September, 14:30 – 14:55Main StageAI agents need more than capable models. They need access to the knowledge that makes enterprise data meaningful: business concepts, relationships and context. What if we organised that knowledge in a shared layer, allowing agents to become thinner, simpler and better grounded? This talk explores how knowledge graphs provide that foundation, connecting enterprise data and semantics to support agentic AI. Through practical examples and customer stories, we will show how a knowledge layer built on Neo4j can help agents retrieve relevant information, navigate connected data and deliver more accurate, explainable results.