Building Automotive Parts Intelligence using Graph Memory for Supply Chain Resilience

Fixing automotive supply chain risk with graphs, vectors, and agents
A chip shortage hits and one part goes dark. Vector search finds parts that look alike. It can't tell you which vehicles are affected, whether a substitute clears compliance, or where supplier concentration creates risk.
In this stream, we build a dual-store architecture - Neo4j for graph reasoning, Qdrant for semantic search - orchestrated by a LangGraph agent that runs impact analysis, validates alternatives against compliance and BOM constraints, and flags supplier risk, end to end.
If you build with graphs, vectors, or agentic pipelines, come see how they hold up under pressure.

Guest: Pavan Vemuri ( linkedin.com/in/pavan-vemuri-77419723 (opens in a new tab) )

@qdrant