Learn with Neo4j's New "Get to Know Graph & GenAI" Webinar Series >>
Session Track: App Dev
Session Time:
Session description
The focus of this talk is on building AI agents that construct and leverage knowledge graphs using the Neo4j Model Context Protocol (MCP) server. You will learn how to rapidly build production-ready AI agents using the Neo4j MCP server. In addition, you will learn to create agents that dynamically construct and curate Neo4j knowledge graphs while using them for agent memory and GraphRAG use cases. This session covers practical implementation strategies for agent-to-Neo4j integration, intelligent curation workflows, and advanced retrieval mechanisms. You will explore architectures that treat knowledge graphs as both memory layers and contextual reasoning foundations. By the end, you will have the tools to rapidly prototype and deploy AI agents that transform unstructured data into knowledge graphs and enhance reasoning capabilities through sophisticated GraphRAG implementations.
Director, Hypermode
William Lyon is director of developer experience at Hypermode, where he helps developers build AI agents using open source tools. Previously, he worked as a software developer at Neo4j and other startups. William is also the author of the book “Fullstack GraphQL Applications” and earned a master's degree in Computer Science from the University of Montana. You can find him online at lyonwj.com.