Built an agentic fraud investigator using

A developer built an agentic fraud investigator on TigerGraph for the HH Goa 2026 hackathon, chaining graph traversal, case memory, a policy engine, and next-best-action recommendations that produce suspicious activity reports. The project, with code on GitHub and a Streamlit demo, argues that because fraud is relational, the underlying database should be graph-based.

Built an Agentic Fraud Investigator using TigerGraph for HHGOA2026 🚀 My agent investigates fraud like an analyst: Graph Traversal - Case Memory - Policy Engine - Next-Best Action + SAR Fraud is relational, so the DB should be too. Repo: https://github.com/foxmaster77/tigergraph https://github.com/foxmaster77/tigergraph LInk : https://tigergraph-2cd6jdrgrem2jblxb49zjj.streamlit.app https://tigergraph-2cd6jdrgrem2jblxb49zjj.streamlit.app @TigerGraphDB @247pmstudio