{
  "id": 9568520,
  "title": "Building an Agentic Fraud Investigation System with TigerGraph, LangGraph & MCP",
  "url": "https://urgent.news/2026/09/24/building-an-agentic-fraud-investigation-system-with-tigergraph",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-24T14:56:24.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/subratkumarpadhy/building-an-agentic-fraud-investigation-system-with-tigergraph-langgraph-mcp-obd"
  },
  "original_language": "en",
  "account": null,
  "summary": "TL;DR : We built a 9-node LangGraph agent that investigates fraud cases end-to-end. It uses TigerGraph Community Edition as the knowledge graph substrate, TigerGraph MCP for tool access, and NVIDIA NIM for LLM reasoning. It produced FinCEN-standard SAR narratives for cases requiring regulatory filing, and wrote every case back to the graph as memory for future investigations. All 20 HHGOA…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}