FeaturesPain Points SolvedAI HighlightsInvestigator Journey

WauGuard.AI

The Guardian of the Digital Sky

BNM AML/CFT Compliant  ·  One-click STR Reports  ·  Explainable AI

Automated AML/CFT Compliance
for the AI Era

Stop losing money to fraud. Stop drowning in false positives.

WauGuard.AI gives your compliance team instant, explainable AI investigations — with BNM-ready STR reports generated in one click. No manual drafting. No black-box decisions. Every alert comes with a full audit trail a BNM examiner can follow.

1-Click

BNM STR Report

Generated automatically — zero drafting

< 100ms

Time to fraud decision

Real-time blocking before money leaves

AWS MY

100% Data Residency

Stays in Malaysia — BNM compliant

≥98%

AI review accuracy

Replaces manual first-pass investigation

Features

Three capabilities that transform
fraud compliance

Legacy systems flag anomalies and stop there. WauGuard.AI gives your compliance team explainable decisions, fewer false positives, and STR reports written automatically.

Explainable AI

Every fraud determination comes with ranked SHAP feature contributions, the rule that fired, and an LLM-written rationale. BNM examiners, auditors, and courts get a traceable reasoning chain — not just a score.

Reduced False Positives with AI

Three intelligence layers — deterministic rules, XGBoost ML, and Neo4j graph context — filter noise before it reaches an analyst. Only the alerts that matter land on your team's desk.

Automated STR Generation

BNM-aligned Suspicious Transaction Reports are generated instantly — Parts A through F, fully formatted, FIED-ready. One click. Zero analyst drafting time.

Pain Points Solved

The problems every Malaysian compliance team faces

BNM pressure is intensifying. Fraud losses are growing. Analyst headcount cannot keep pace. WauGuard.AI was built to solve these exact problems.

The Pain

High BPO & Manual Review Costs

Every flagged transaction requires an analyst to manually review evidence, draft a Suspicious Activity Report, and file with BNM FIED. At scale, this is a headcount problem — not a fraud problem.

The Solution

Automated Case Review with SAR-Ready Export

The Multi-Agent AI Framework writes the complete forensic brief automatically — graph assessment, ML evidence, and regulatory recommendation. Analysts review and confirm; they no longer draft. One click exports a fully formatted BNM STR/SAR PDF.

3-agent AI narrativeOne-click SAR PDFZero drafting time

The Pain

“Black Box” AI — BNM Won't Accept It

Legacy ML models produce a risk score with no explanation. BNM examiners, auditors, and courts require a traceable reasoning chain — not just a number. Opaque models create regulatory and reputational liability.

The Solution

Explainable AI with Full Audit Trails

Every determination is grounded in SHAP feature contributions, named rule triggers (R001–R007), graph community evidence, and an LLM-written rationale. The complete reasoning chain is stored, timestamped, and exportable for any BNM audit.

SHAP per predictionNamed rule triggersImmutable audit log

AI Highlights

The Hybrid Cascade Engine

Three AI tiers working in sequence — each layer adds context the previous one cannot see. Fast enough for real-time blocking. Deep enough for BNM audit.

Tier 1

ML Engine

XGBoost · SHAP

15-feature XGBoost classifier scores every transaction in microseconds. SHAP values are computed alongside every prediction — providing the explainability mandatory under BNM AML/CFT.

Velocity checksRule engine (R001–R007)Calibrated threshold 0.3612
Tier 2

Graph Engine

NetworkX · Neo4j

Account, device, and merchant nodes are linked in a graph. Louvain community detection identifies fraud rings — exposing mule networks that transaction-level ML cannot see alone.

Fraud ring detectionPageRank scoring2-hop investigation graphs
Tier 3

Multi-Agent AI Framework

3-Agent Claude Consensus

Three sequential Claude agents — Graph Sentry, ML Specialist, and Lead Auditor — each analyse a different evidence dimension before synthesising into a BNM-ready forensic brief. One-click SAR export included.

Multi-agent consensus narrativePDPA PII gate enforcedOne-click SAR PDF export

Investigator Journey

From alert to BNM report in three steps.

01

Alert Arrives in Investigation Center

Every flagged or blocked transaction surfaces as a case. No triage needed — risk level, ML score, and rule trigger are already attached.

02

AI Brief is Ready Instantly

The Multi-Agent AI Framework has already written the full forensic brief — graph community risk, SHAP evidence, velocity pattern, and a compliance-ready narrative. The STR PDF is one click away.

03

Confirm or Dismiss — With Full Context

Investigators review the AI reasoning, add notes, and record their verdict. The complete decision chain — AI + human — is stored, timestamped, and audit-ready for BNM.

Powered by Claude AI (Anthropic)

The Multi-Agent AI Framework — 3-agent consensus intelligence

Three sequential Claude agents each analyse a distinct dimension of the evidence: Graph Sentry evaluates the account's community risk, ML Specialist interprets SHAP contributions and velocity signals, and Lead Auditor synthesises both into a compliance-ready forensic brief — in seconds, not analyst-hours.

  • 3-agent consensus — richer than any single-model output
  • Grounded in SHAP feature importance — no hallucination
  • Compliance-ready language for BNM auditors
  • One-click SAR PDF export — FIED-ready in seconds
AI Investigation Report
HIGH RISK
TX-8A4F2C91·Score: 0.8731·claude-3.5-sonnet

[Risk Assessment]

Transaction TX-8A4F2C91 is assessed as HIGH risk with fraud probability 0.8731. Rule R003 triggered on high-risk merchant category.

[Key Evidence]

  • amount_log contributed +0.42 to fraud probability
  • Crypto exchange merchant — elevated category risk
  • Graph: account linked to known fraud ring (Community #14)

[Recommended Action]

Escalate to senior analyst for enhanced due diligence review.

✓ Confirm✗ DismissAnalyst verdict logged

Infrastructure

100% Data Residency in AWS Malaysia

All transaction data, fraud reports, and investigator notes are stored and processed exclusively within AWS ap-southeast-5 (Malaysia) — satisfying BNM data localisation requirements without compromise.

AWS ap-southeast-5

Malaysia region — data never leaves MY

RDS PostgreSQL 16

Multi-AZ, managed backups

Neo4j on EC2

Graph DB in-region

VPC isolation

No public DB endpoints

Cost-Optimised for Financial Institutions

WauGuard.AI eliminates dedicated fraud analyst headcount for first-pass investigation. LLM-as-a-Service economics mean the cost per investigation brief is a fraction of manual review — scaling linearly with transaction volume, not headcount.

Built for Malaysian Financial Regulation

BNM AML/CFT Framework
Zero PII exposure
Explainable AI on every alert
Immutable audit trail

Ready to stop writing SARs
by hand?

Log in and run your first AI-powered fraud investigation — with a BNM-ready STR in one click.

Access the Platform