AI Career Twin: A Human–AI Collaborative Framework for Dynamic Skill-Gap Analysis and Personalized Career Guidance

AI Career Twin is a proposed human–AI collaborative framework designed to support personalized career guidance, dynamic skill-gap analysis, and informed career decision-making. The framework addresses the limitations of traditional career recommendation systems, which often rely on static profiles and provide recommendations without considering evolving skills, changing industry requirements, or the uncertainty of available evidence. The proposed framework maintains a dynamic, time-indexed digital representation of an individual’s educational background, technical skills, professional experience, projects, certifications, career goals, and personal preferences. It integrates evidence-based skill assessment, labor-market analysis, explainable role recommendations, personalized learning pathways, and retrieval-augmented generation (RAG) to provide transparent and context-aware career guidance. Key components of the proposed framework include: Dynamic skill profiling with separate proficiency and confidence estimates. Evidence-based skill-gap analysis using time-stamped labor-market information. Personalized career-role recommendations based on skills, goals, and constraints. Adaptive learning-path suggestions considering time, cost, and prerequisites. Retrieval-grounded AI mentoring with source citations and uncertainty handling. Human–AI collaboration through user feedback, corrections, and scenario-based career exploration. The paper presents the proposed system architecture, mathematical formulations, algorithmic methodology, and a structured evaluation protocol covering recommendation accuracy, skill-gap correctness, mentoring quality, and user interaction. Research Status: This publication presents a conceptual framework and proposed evaluation methodology. The system has not yet been implemented or experimentally evaluated. Future work includes prototype development, empirical validation, and user-centered evaluation. The research aims to establish a foundation for transparent, explainable, and evidence-based AI-assisted career guidance while preserving human control over career decisions. Keywords: Artificial Intelligence, AI Career Twin, Human Digital Twin, Career Guidance, Skill-Gap Analysis, Personalized Recommendations, Retrieval-Augmented Generation, Explainable AI, Human–AI Collaboration.