Agentic AI for Financial Crime Compliance

2025-09-16

AI Summary

Financial crime compliance (FCC) is costly, inefficient, and hindered by AI solutions lacking interpretability and regulatory alignment. To address this, we propose a regulatory-compliance-oriented autonomous agent reference architecture featuring role-based separation of duties, task-driven model routing, and auditable provenance tracking—enabling end-to-end automation of customer onboarding, monitoring, investigation, and reporting, thereby embedding “compliance-by-design.” Integrating artifact modeling, Action Design Research (ADR), and multi-stakeholder co-development, we implement and deploy a prototype on a real-world digital financial platform. Empirical evaluation demonstrates significant improvements in compliance efficiency and decision transparency, while fully satisfying regulatory requirements for traceability and verifiability. This work establishes the first agent-based compliance paradigm in information systems that simultaneously ensures regulatory fitness and engineering feasibility.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The cost and complexity of financial crime compliance (FCC) continue to rise, often without measurable improvements in effectiveness. While AI offers potential, most solutions remain opaque and poorly aligned with regulatory expectations. This paper presents the design and deployment of an agentic AI system for FCC in digitally native financial platforms. Developed through an Action Design Research (ADR) process with a fintech firm and regulatory stakeholders, the system automates onboarding, monitoring, investigation, and reporting, emphasizing explainability, traceability, and compliance-by-design. Using artifact-centric modeling, it assigns clearly bounded roles to autonomous agents and enables task-specific model routing and audit logging. The contribution includes a reference architecture, a real-world prototype, and insights into how Agentic AI can reconfigure FCC workflows under regulatory constraints. Our findings extend IS literature on AI-enabled compliance by demonstrating how automation, when embedded within accountable governance structures, can support transparency and institutional trust in high-stakes, regulated environments.

Problem

• Rising costs and complexity in financial crime compliance
• Opaque AI solutions misaligned with regulatory expectations
• Automating compliance workflows while ensuring transparency and trust

Innovation

• Agentic AI system automates compliance workflows
• Explainable traceable compliance-by-design architecture
• Artifact-centric modeling with autonomous agent roles