# CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments Source: [CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments]() Collection index: [llms.txt]() Data updated: 2026-05-05T05:00:04.460Z Authors: Nitish Jaipuria, Lorenzo Gatto, Zijun Kan, Shankey Poddar, Bill Cheung, Diksha Bansal, Ramanan Balakrishnan, Aviral Suri, Jose Estevez Published: 2025-08-27T14:47:33.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Scam Detection Conversational Evaluation on Google Pay India (Pre-Production)](): Scam Detection Conversational Evaluation; Google Pay India (Pre-Production); Topic Adherence: 99.9. - [Scam Detection Conversational Evaluation on Google Pay India (Post-Production)](): Scam Detection Conversational Evaluation; Google Pay India (Post-Production); Topic Adherence: 99.9. ## Original sources and implementation [Original paper]() [PDF]()