# Necromancer

- **Event:** [Google DeepMind Bangalore Hackathon](https://cerebralvalley.ai/e/google-deepmind-bangalore-hackathon)
- **When:** Sat, Jul 11 at 9:00 AM – 10:00 PM (GMT+5:30)
- **Where:** Marathahalli, Marathahalli Main Road
- **Team:** [Vedant Yadav](https://cerebralvalley.ai/u/Vedanntttt)
- **GitHub:** https://github.com/vedanntttt/agentic-fraud-detection
- **Demo video:** https://youtu.be/U1541eoyb_U
- **Gallery:** https://cerebralvalley.ai/e/google-deepmind-bangalore-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/google-deepmind-bangalore-hackathon/hackathon/gallery/135

I ahve built a agentic fraud detection sysgtem which uses 3 agents to flag the chained fraud transaction which is the ost effective fraud trick.
UPI Fraud Investigation Agents — a multi-agent system that investigates suspected UPI mule-account fraud, and is designed to distrust its own conclusions.

Three agents run in a loop:

Detector — an XGBoost model (trained on the public IBM AML dataset) flags suspicious account clusters. It's tuned recall-first: it catches ~75% of mule transactions, at the cost of about 1 in 4 flags being a false alarm.
Investigator — a Gemini managed agent that writes and runs its own graph-traversal code in a cloud sandbox, tracing the fund flow hop by hop.
Judge — a Gemini agent that critiques the trace against explicit evidence criteria. Weak traces get rejected and sent back for re-investigation (capped at 3 passes); genuinely ambiguous cases get handed to a human rather than guessed at.

---

Markdown version of https://cerebralvalley.ai/e/google-deepmind-bangalore-hackathon/hackathon/gallery/135. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt