#graphdatabase

An agentic fraud investigator on TigerGraph: GSQL, GraphRAG, MCP, and a deterministic policy core the LLM cannot touch.

Technical write-up for the TigerGraph Agentic Fraud Investigation hackathon (Hacker House Goa). The...

How we built a policy-constrained fraud investigation system combining TigerGraph multi-hop retrieval, MCP stdio tools, deterministic banking policy rules, and persistent graph case memory.

Watch the 4-minute demo: https://youtu.be/hMCUqjbN9js?si=wJPxXt_Av67RlP4x The model...

How Team Vajra built an agentic GraphRAG system using TigerGraph 4.2.5, LangGraph, and Google Gemini 2.5 Flash Lite to uncover payment fraud rings.

dataset — 590,742 transactions, 5,565 closed investigations, 20 exam cases.* ...

An agentic fraud triage system that uses TigerGraph GraphRAG to map fraud rings, reason over real graph paths, and generate compliance-ready SARs.

Kavach: building a fraud investigator that knows when a risk score is lying TigerGraph x...

I opened Claude to reason about a schema change. Then Cursor, to make it. Then Claude again the next...

Most retrieval stacks start with a vector index, and for good reason: "find me things that look like...

I asked three pipelines one question from the TigerGraph Agentic GraphRAG Hackathon benchmark: how...

I benchmarked 5 managed graph databases — and the "obvious" winner changed depending on what I...