The Data Exchange with Ben Lorica Building the Knowledge Layer Your Agents Need
10 snips
Nov 26, 2025 Philip Rathle, CTO of Neo4j and a leading expert in graph technologies, explores the integration of knowledge graphs in enterprise AI. He discusses the real-world application of GraphRAG, detailing how it enhances context for AI agents. Rathle highlights successful enterprises using this technology and warns against overly complex projects. He also showcases tools like the LLM Graph Builder for building starter knowledge graphs and emphasizes the need for clear governance and determinism in AI systems, ultimately illustrating how graphs can significantly improve AI reasoning.
AI Snips
Chapters
Transcript
Episode notes
Unstructured Data Hides Implicit Structure
- Unstructured text often contains implicit structure that can be distilled into relationships.
- Philip Rathle says knowledge graphs capture distilled relationships as a useful form of context for models.
Walmart Use Case: Large-Scale Employee Feedback
- Philip describes Walmart using a graph-app to synthesize employee feedback from 1.6 million employees to inform managers.
- That project reportedly improved identification of target compounds 50x and shortened drug-discovery timelines.
Start Small With A Starter Knowledge Graph
- Start with a high-value business problem and build a starter knowledge graph rather than boiling the ocean.
- Use an iterative approach: refine the graph over time to meet enterprise needs like accuracy and explainability.