Overview
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.
