← Back to Projects
Risk AnalyticsAI AgentRAGLLM

AML Sentinel: China AML Investigation Workbench

A bank-style AML compliance workbench combining real Chinese financial fraud data (DGraph-Fin by Finvolution), PBOC regulatory RAG, and an AI Agent that auto-drafts Suspicious Transaction Reports — designed around the full analyst investigation workflow.

10 min read
Interactive Demo
4 tech tags

Overview

AML Sentinel is a portfolio-grade prototype of a bank AML investigation and reporting platform. It models the full compliance workflow: alert triage, case investigation, regulation lookup, and STR drafting — each step grounded in China's regulatory framework. Transaction data is preprocessed from DGraph-Fin (Finvolution, NeurIPS 2022) and IBM AML (NeurIPS 2023). The regulatory knowledge base covers the revised 反洗钱法 2024, FATF China 2019 Mutual Evaluation, and KPMG's compliance analysis. The STR generator deploys a 6-step Anthropic claude-sonnet-4-6 Agent that autonomously investigates a flagged case and produces a draft Suspicious Transaction Report in CAMLMAC format.

Key Features

01

Alert Queue

PBOC threshold rules applied to transaction data; severity triage (Critical / High / Medium / Low) with rule explanations and risk score breakdowns from DGraph-Fin ML scores

02

Case Overview

Structured case lifecycle (6 states), key findings, reporting urgency countdown, analyst notes with handoff to supervisor review

03

Investigation Workspace

ECharts force-directed graph with fan-out, fan-in, and cycle pattern highlighting from IBM AML HI-Small typology labels; investigation checklist

04

Regulation Copilot

Hybrid BM25 + Anthropic API Q&A over 反洗钱法 2024, FATF China MER 2019, and KPMG AML analysis; every answer cites specific article or section references

05

STR Auto-Draft

6-step AI Agent using claude-sonnet-4-6 tool_use: case extraction, account analysis, regulation retrieval, typology classification, urgency assessment, CAMLMAC-format report generation

Methodology

Data layer: DGraph-Fin node features mapped to alert risk signals; IBM AML HI-Small provides labeled laundering typology patterns for the network graph. Regulatory RAG uses CJK-aware BM25 retrieval to fetch top-5 chunks from ~80 pre-chunked regulatory excerpts, then passes them to Anthropic claude-sonnet-4-6 via streaming API for grounded answer generation. STR generation uses an agentic tool_use loop: Claude iteratively calls 5 deterministic tools, then produces a structured STR draft in CAMLMAC format. The system always maintains human-in-the-loop: AI output is advisory, never auto-submitted.

Tech Stack

Risk AnalyticsRISK
AI AgentAGENT
RAGRAG
LLMLLM

Project Info

Read time10 min
Live demoAvailable
FeaturedYes
Tags4
← Back to Projects
Dedicated Product Page · Full Interactive Workbench

Launch AML Sentinel Workbench

Alert triage → Case investigation → Network graph → Regulatory RAG → AI Agent STR drafting. Full product experience.

84
Real Alerts
71
AML Cases
55
Regulation Chunks
6
Agent Steps
Open Full Workbench