HACKATHON DEMO · REAL-TIME

Multi-Agent
Fraud Detection

A hierarchical AI system where Claude acts as the brain —
orchestrating specialized agents to catch fraud in real time

Claude 3.5 Sonnet · GraphSAGE · Redis Stream · MCP Tools

The Problem

Fraud hides in connections,
not individual transactions

Money laundering works by moving funds through a ring of accounts. Each transfer looks normal — the fraud only appears when you look at the whole network.

$3.1T
LAUNDERED ANNUALLY
0.1%
CURRENTLY DETECTED
Real-time
OUR DETECTION SPEED
Architecture

4 Agents, 1 Brain

📡
Data Agent
Redis Stream · live feed
🕸️
Graph Agent
NetworkX · PyG · topology
🧠
Orchestrator
Claude 3.5 Sonnet
ReAct Loop
🧬
Inference Agent
GraphSAGE · /predict
🚨
Alert Agent
Structured output · dispatch
Step 2 — Standardized Interfaces

MCP Tools: clear contracts
between Claude and each agent

predict_fraud
GNN model scores src + dst account fraud probability
get_account_history
Risk profile, tx frequency, high-risk neighbor count
get_graph_topology
Cycle detection, degree centrality, 2-hop neighbors
get_stream_stats
Live Redis Stream: consumed count, fraud edges, graph size
dispatch_action
Execute BLOCK / HUMAN_REVIEW / ALLOW based on evidence
JSON Schema
Every tool has typed inputs — Claude knows exactly what to pass
Step 3 — Agentic Loop

ReAct: Reason → Act → Observe
Claude decides how deep to dig

💬
Transaction In
New suspicious tx
🤔
Reason
Claude picks tool
⚙️
Act
Call MCP tool
👁️
Observe
Read result
📋
Report
Enough evidence?
↩ If more evidence needed — loop back and call another tool autonomously

Claude autonomously decides: score first → check history → verify graph topology → dispatch

Step 4 — Automated Response

3-Level Risk Dispatcher

≥ 0.8
🚫 BLOCK + Full Trace Report
Transaction intercepted · Orchestrator triggers multi-hop chain tracing · Structured report generated
0.3–0.8
👁️ HUMAN REVIEW Queue
Transaction allowed · Flagged for analyst review · Human-in-the-loop decision
< 0.3
✅ ALLOW + Async Update
Fast pass-through · Graph features updated asynchronously in background
Step 5 — Hackathon Demo

Catching a money laundering ring

1
A $181,097 TRANSFER comes in — looks like a normal transaction on the surface
2
Claude calls predict_fraud → GNN scores sender at 0.85 — high risk flag triggered
3
Claude calls get_account_history14 transactions in 24 hours, classic structuring pattern
4
Claude calls get_graph_topology → detects 4-node cycle — circular fund flow confirmed
5
Claude calls dispatch_action(HIGH) → transaction BLOCKED + full investigation report generated
Summary

Modular, decoupled,
and production-ready

LIVE DEMO
python -m orchestrator.demo_runner