PersoPilot: An Adaptive AI-Copilot for Transparent Contextualized Persona Classification and Personalized Response Generation

TL;DR

PersoPilot tackles the problem of context-insensitive personalization by unifying persona understanding with contextual reasoning in a dual-mode AI copilot. The approach combines a live user-facing PersoAgent with an analyst-facing Analytic Tools backend, integrating a BERT-based Persona Extractor, a Community-based Recommender, Phi-4 mini for explanation-enabled labeling, and a TF-IDF classifier within a prompt-driven framework. It enables transparent, task-aware personalization and scalable annotation via an active learning loop, with a publicly available implementation and demo. The work advances explainable, adaptive personalization across user and analyst workflows, with potential applicability to broad service personalization domains.

Abstract

Understanding and classifying user personas is critical for delivering effective personalization. While persona information offers valuable insights, its full potential is realized only when contextualized, linking user characteristics with situational context to enable more precise and meaningful service provision. Existing systems often treat persona and context as separate inputs, limiting their ability to generate nuanced, adaptive interactions. To address this gap, we present PersoPilot, an agentic AI-Copilot that integrates persona understanding with contextual analysis to support both end users and analysts. End users interact through a transparent, explainable chat interface, where they can express preferences in natural language, request recommendations, and receive information tailored to their immediate task. On the analyst side, PersoPilot delivers a transparent, reasoning-powered labeling assistant, integrated with an active learning-driven classification process that adapts over time with new labeled data. This feedback loop enables targeted service recommendations and adaptive personalization, bridging the gap between raw persona data and actionable, context-aware insights. As an adaptable framework, PersoPilot is applicable to a broad range of service personalization scenarios.

Figures (4)

• Figure 1: Architectural overview of the PersoPilot framework.
• Figure 2: User interface for the help seeker showing personalized assistance features.
• Figure 3: Analyst workflow showing (a) classification task setup, and (b) labeling assistant output for analyst review, update, and confirmation.
• Figure 4: User classification results interface with prediction accuracy, and recent classification outcomes.