Dynamic Agentic AI Expert Profiler System Architecture for Multidomain Intelligence Modeling

TL;DR

This paper introduces a layered AI system that classifies user expertise levels in real-time during human-AI interactions, improving contextual understanding across diverse domains.

Contribution

It presents a novel modular architecture based on LLaMA v3.1 for dynamic expertise profiling in multi-domain settings, validated through extensive live and recorded evaluations.

Findings

83% to 97% accuracy in matching self-assessed expertise levels

Effective real-time expertise assessment during live interviews

Identified sources of discrepancies such as bias and misinterpretation

Abstract

In today's artificial intelligence driven world, modern systems communicate with people from diverse backgrounds and skill levels. For human-machine interaction to be meaningful, systems must be aware of context and user expertise. This study proposes an agentic AI profiler that classifies natural language responses into four levels: Novice, Basic, Advanced, and Expert. The system uses a modular layered architecture built on LLaMA v3.1 (8B), with components for text preprocessing, scoring, aggregation, and classification. Evaluation was conducted in two phases: a static phase using pre-recorded transcripts from 82 participants, and a dynamic phase with 402 live interviews conducted by an agentic AI interviewer. In both phases, participant self-ratings were compared with profiler predictions. In the dynamic phase, expertise was assessed after each response rather than at the end of the interview. Across domains, 83% to 97% of profiler evaluations matched participant self-assessments. Remaining differences were due to self-rating bias, unclear responses, and occasional misinterpretation of nuanced expertise by the language model.