Context Engineering: Connecting the Dots with Graphs
summary
Neo4j Aura hosts a 135-node, 418-relationship knowledge graph built from a BOM and a VEX file using an open-source knowledge graph builder, then used two demos: a vector-plus-graph pipeline that returns grounded CVE nodes and a Claude + Neo4j Cypher MCP flow that incrementally queries schema and returns CVE details, CVSS severities and a version fix (e.g. affected v2.10), proving graph RAG gives more relevant, explainable results and supports connected memory.
AI-written summary · about
chapters (8)
- 0:00Introduction and setup
- 1:41From prompt to context engineering
- 5:52Why context engineering matters now
- 8:19Knowledge graphs explained
- 13:17Demo building a knowledge graph
- 17:57Memory retrieval with graphs
- 23:13Demo querying with graph tools
- 26:17Resources and closing
related talks
49mConnecting the Dots with Context Graphs
56mConnecting the Dots with Context Graphs
30mAgentic RAG with Knowledge Graphs Explained
31mSix Degrees of Infiltration
32mUnderstanding Complexly Connected Data using Graph Databases
23mConnecting the Dots With Context Graphs
30mNeo4j Product Vision and Roadmap
01h 00mGraph Mastery to AI