From Surface Learning to Deep Understanding: A Grounded AI Tutoring System for Moodle

TL;DR

This paper introduces a Moodle plugin that uses Retrieval-Augmented Generation to provide accurate, grounded AI tutoring, enhancing deep understanding and reducing misinformation for students and educators.

Contribution

The development of a modular, grounded AI tutoring system with a dual-centric design and evaluation demonstrating high faithfulness and user satisfaction.

Findings

Achieved faithfulness scores up to 0.97

Received a 4.00/5.00 recommendation rate in user study

Effectively grounded responses in teacher-provided materials

Abstract

This demo paper describes the development of the AI Teaching \& Learning Assistant, a modular Moodle plugin that leverages Retrieval-Augmented Generation (RAG) to deliver high-quality, hallucination-free education. The system employs a dual-centric design, providing students with interactive, Socratic-based tutoring and educators with a "human-in-the-loop" workspace for supervised content generation. By grounding Large Language Model (LLM) responses in teacher-provided materials, the assistant addresses the risks of misinformation while encouraging deep conceptual mastery. Evaluation via the Ragas (LLM-as-a-Judge) framework and a preliminary user study confirms its effectiveness, achieving faithfulness scores up to 0.97 and a 4.00/5.00 recommendation rate.