AI PB: A Grounded Generative Agent for Personalized Investment Insights
This addresses the problem of delivering reliable AI-driven investment advice for retail finance users, though it is incremental as it builds on existing methods with domain-specific adaptations.
The paper tackles the challenge of providing personalized investment insights in retail finance by deploying AI PB, a generative agent that proactively generates grounded and compliant insights, resulting in a system that operates on-premises with 24 NVIDIA H100 GPUs and demonstrates trustworthy AI insights through human QA and system metrics.
We present AI PB, a production-scale generative agent deployed in real retail finance. Unlike reactive chatbots that answer queries passively, AI PB proactively generates grounded, compliant, and user-specific investment insights. It integrates (i) a component-based orchestration layer that deterministically routes between internal and external LLMs based on data sensitivity, (ii) a hybrid retrieval pipeline using OpenSearch and the finance-domain embedding model, and (iii) a multi-stage recommendation mechanism combining rule heuristics, sequential behavioral modeling, and contextual bandits. Operating fully on-premises under Korean financial regulations, the system employs Docker Swarm and vLLM across 24 X NVIDIA H100 GPUs. Through human QA and system metrics, we demonstrate that grounded generation with explicit routing and layered safety can deliver trustworthy AI insights in high-stakes finance.