Ben Lackey

SQL is foundational to Snowflake, but layering relationship intelligence provides a competitive edge. In this workshop, discover how to extend SQL workflows by integrating Neo4j's graph analytics directly into the AI Data Cloud. Using a manufacturing risk scenario, you will model operational data into a graph and apply several different similarity algorithms to uncover systemic risks. Master a scalable, zero-ETL pattern applicable to any industry to enrich your SQL insights with graph-native power. Key learnings include how to: Merge SQL precision with graph depth Deploy Neo4j Graph Analytics in Snowflake Apply graph-based similarity Build scalable, relationship-aware intelligence

Combining generative AI with knowledge graphs enhances language understanding and generates more contextually accurate responses. This enriches information retrieval and context-based reasoning, and improves the overall user experience.

Featurization is one of the most difficult problems in machine learning, just behind data wrangling in terms of the time it consumes. For many problems, featurization plays the largest role in determining model performance, greater even than choice of machine learning method.