Road to NODES 2026 | Build Your First Knowledge Layer

Your agent can reach your data but still can't use it reliably: vector search and Text2SQL each hand it a slice, but not the view to know what's truly relevant and how to connect the right info. Without that, answers come back confident but wrong, and agent decisions can't be trusted. The problem isn't a bad model or a bad query - it's a lack of context, and thinking in terms of shapes in a knowledge layer is what cracks it. The workshop includes hands-on exercises where you build a lightweight knowledge layer on top of your existing documents and SQL data using Neo4j, structured around three shapes. You'll build a Table of Contents (Trees) to navigate documents, surface Themes (Communities) that reveal patterns nobody named, and trace Connections (Semantic Layer) to show how structured entities and records relate to each other. Each shape is built hands-on with real code you can take home and rerun against your own data. By the end of the session, you'll have a working knowledge layer your agent can navigate to answer and act accurately, plus hands-on exposure to the latest Neo4j CLI and skill bundles for text2Cypher and agentic coding with Neo4j. You'll leave with practical techniques for turning mixed structured and unstructured data into context an agent can actually reason over.