From Messy Documents to a Queryable KYC Knowledge Graph Live Build with Quark Labs & Memgraph

KYC documents are full of handwritten numbers, half-ticked checkboxes, and inconsistent layouts. What happens when you extract all of that - confidence scores included - and connect it across 20+ documents in a knowledge graph? Vishal Singh (Quark Labs) will live-build a KYC knowledge graph from real-world investor services documents - handwritten fields, checkboxes, multi-column layouts, the lot. You'll see how Quark Labs' document intelligence pipeline extracts entities with confidence scoring and pixel-level lineage, then pushes them into Memgraph where cross-document entity resolution connects the same customer across multiple filings. The demo covers the full loop: raw scanned documents → entity extraction → knowledge graph in Memgraph Lab → natural language queries against the graph. No slides. No theory. Just documents in, answers out. About Memgraph: Memgraph is a high-performance, in-memory graph database that powers real-time AI context. It serves as the graph engine for GraphRAG pipelines, AI memory systems, and agentic workflows - delivering sub-millisecond multi-hop traversals with full provenance for any system that needs structured, connected context alongside semantic search. The same architecture that makes Memgraph the context layer for AI also drives real-time graph analytics across fraud detection, network analysis, infrastructure monitoring, and other operational use cases where speed and connectivity matter. Website: https://www.memgraph.com Twitter: https://www.twitter.com/memgraphdb LinkedIn: https://www.linkedin.com/company/memgraph Facebook: https://www.facebook.com/memgraph