# CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments

## TL;DR

This paper introduces CASE, an AI framework that uses conversational agents to gather scam intelligence from victims, improving scam enforcement in digital payments.

## Contribution

The paper presents a novel agentic AI system that proactively collects scam data via conversations, enhancing scam detection and enforcement in digital payment platforms.

## Key findings

- 21% increase in scam enforcement volume on Google Pay India
- Framework is highly generalizable to other domains
- Uses Google's Gemini LLMs for implementation

## Abstract

The proliferation of digital payment platforms has transformed commerce, offering unmatched convenience and accessibility globally. However, this growth has also attracted malicious actors, leading to a corresponding increase in sophisticated social engineering scams. These scams are often initiated and orchestrated on multiple surfaces outside the payment platform, making user and transaction-based signals insufficient for a complete understanding of the scam's methodology and underlying patterns, without which it is very difficult to prevent it in a timely manner. This paper presents CASE (Conversational Agent for Scam Elucidation), a novel Agentic AI framework that addresses this problem by collecting and managing user scam feedback in a safe and scalable manner. A conversational agent is uniquely designed to proactively interview potential victims to elicit intelligence in the form of a detailed conversation. The conversation transcripts are then consumed by another AI system that extracts information and converts it into structured data for downstream usage in automated and manual enforcement mechanisms. Using Google's Gemini family of LLMs, we implemented this framework on Google Pay (GPay) India. By augmenting our existing features with this new intelligence, we have observed a 21% uplift in the volume of scam enforcements. The architecture and its robust evaluation framework are highly generalizable, offering a blueprint for building similar AI-driven systems to collect and manage scam intelligence in other sensitive domains.