# RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented Tutoring

## TL;DR

This paper introduces RAG-PRISM, an adaptive AI-driven tutoring framework that personalizes cybersecurity training for 4IR workforce development, leveraging retrieval-augmented generation and large language models for rapid, relevant, and scalable skill mastery.

## Contribution

It presents a novel adaptive tutoring framework combining generative AI with retrieval-augmented methods for personalized, rapid skill training in 4IR contexts, validated through cybersecurity case studies.

## Key findings

- GPT-4 achieved 87% relevancy in training responses.
- The framework effectively personalizes content based on learner profiles.
- RAG-PRISM outperforms traditional methods in content relevance and alignment.

## Abstract

The rapid digital transformation of Fourth Industrial Revolution (4IR) systems is reshaping workforce needs, widening skill gaps, especially for older workers. With growing emphasis on STEM skills such as robotics, automation, artificial intelligence (AI), and security, large-scale re-skilling and up-skilling are required. Training programs must address diverse backgrounds, learning styles, and motivations to improve persistence and success, while ensuring rapid, cost-effective workforce development through experiential learning. To meet these challenges, we present an adaptive tutoring framework that combines generative AI with Retrieval-Augmented Generation (RAG) to deliver personalized training. The framework leverages document hit rate and Mean Reciprocal Rank (MRR) to optimize content for each learner, and is benchmarked against human-generated training for alignment and relevance. We demonstrate the framework in 4IR cybersecurity learning by creating a synthetic QA dataset emulating trainee behavior, while RAG is tuned on curated cybersecurity materials. Evaluation compares its generated training with manually curated queries representing realistic student interactions. Responses are produced using large language models (LLMs) including GPT-3.5 and GPT-4, assessed for faithfulness and content alignment. GPT-4 achieves the best performance with 87% relevancy and 100% alignment. Results show this dual-mode approach enables the adaptive tutor to act as both a personalized topic recommender and content generator, offering a scalable solution for rapid, tailored learning in 4IR education and workforce development.