IntermediateTutorialOct 15, 2026Migrating from Neo4j to TigerGraph: A Practical Architecture, Data, and Query PlaybookMoving from Neo4j to TigerGraph? Learn how to assess your architecture, map your data model, handle Cypher queries, and validate performance before cutover.Discover
Talk39 min · Oct 5, 2026The Identity Layer for AI — Transforming AML & KYC with Graph Powered Entity Resolution 1920AI can detect patterns across millions of transactions. But when the same person or business appears across different accounts, devices, addresses, and records, AI faces a fundamental problem: it may not know who it is actually looking at.Discover
WebinarSep 23, 2026The Identity Layer for AI: Transforming AML & KYC with Graph-Powered Entity ResolutionDiscover
Talk37 min · Sep 3, 202680 7% Fewer Tokens What 300+ GraphRAG Applications RevealedMost RAG systems retrieve too much context and leave the language model to find the signal. GraphRAG changes the equation by retrieving connected evidence instead of isolated passages. Across TigerGraph’s GraphRAG hackathons, more than 300Discover
IntermediateTutorialAug 18, 2026Hands-On with Context Graphs: Build an Agentic Memory Layer with TigerGraphAI agents forget between sessions. Learn how to build a TigerGraph context graph that gives your agent persistent, relationship-aware memory in five steps.Discover
Talk40 min · Aug 5, 2026TigerGraph 4.3 Built for Enterprise Security, Integration, and ScaleEnterprise AI adoption continues to accelerate, but many graph platforms still face a major limitation: They were not built to fit naturally into enterprise environments. Many organizations can prove the value of graph technology. But gettDiscover
ConceptAug 4, 2026Advanced RAG Techniques: From Naive RAG to Hybrid GraphRAGDiscover advanced RAG techniques that fix retrieval quality ceilings, from chunking and re-ranking to GraphRAG and hybrid GraphRAG. Find the right architecture for your enterprise AI workload.Discover
Talk36 min · Jul 1, 2026From Connected Data to Hidden Fraud Rings Mule Detection with Graph Neural NetworksBanks know about the mule accounts they have already found. The real challenge is finding the ones they haven't. Most fraud detection systems rely on rules, alerts, and connections to previously identified fraudsters. As a result, they areDiscover
Talk53 min · May 30, 2026Architecting AI That Banks Can Trust Why Knowledge Graphs Are the Missing LayerBanks are deploying AI across fraud detection, AML, underwriting, customer servicing, and real-time decisioning. But as these systems move deeper into production, a critical problem is emerging: AI can only evaluate the context it can see.Discover
Talk35 min · May 8, 2026Your AI Can't See Fraud Here's WhyYour AI isn’t failing, but it is making decisions without the relationships that define how fraud works. Fraud does not happen in a single transaction. It emerges across identities, devices, accounts, and time. Yet most systems still evaluDiscover