AI PB: A Grounded Generative Agent for Personalized Investment Insights

TL;DR

AI PB is a scalable, grounded generative agent designed for personalized, compliant investment insights in retail finance, integrating routing, retrieval, and layered safety to ensure trustworthy AI in high-stakes environments.

Contribution

The paper introduces AI PB, a novel production-scale generative agent that combines deterministic routing, hybrid retrieval, and multi-stage recommendation for personalized financial insights.

Findings

Grounded generation with explicit routing improves trustworthiness.

Layered safety mechanisms ensure compliance and reliability.

System achieves high-quality, personalized insights in real-world finance settings.

Abstract

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.