An Experience Report on a Pedagogically Controlled, Curriculum-Constrained AI Tutor for SE Education

TL;DR

This paper reports on the design and pilot evaluation of RockStartIT Tutor, an AI-powered, curriculum-constrained tutoring system for secondary school programming education, demonstrating its potential to support personalized learning and reduce cognitive load.

Contribution

It introduces a novel prompting strategy and knowledge base for AI tutors, emphasizing curriculum constraints and practical deployment without model training.

Findings

Learners valued low-stakes question asking and scaffolded guidance.

Educators saw potential in reducing cognitive load and supplementing classroom teaching.

System shows promise despite prototype limitations and small sample size.

Abstract

The integration of artificial intelligence (AI) into education continues to evoke both promise and skepticism. While past waves of technological optimism often fell short, recent advances in large language models (LLMs) have revived the vision of scalable, individualized tutoring. This paper presents the design and pilot evaluation of RockStartIT Tutor, an AI-powered assistant developed for a digital programming and computational thinking course within the RockStartIT initiative. Powered by GPT-4 via OpenAI's Assistant API, the tutor employs a novel prompting strategy and a modular, semantically tagged knowledge base to deliver context-aware, personalized, and curriculum-constrained support for secondary school students. We evaluated the system using the Technology Acceptance Model (TAM) with 13 students and teachers. Learners appreciated the low-stakes environment for asking questions and receiving scaffolded guidance. Educators emphasized the system's potential to reduce cognitive load during independent tasks and complement classroom teaching. Key challenges include prototype limitations, a small sample size, and the need for long-term studies with the target age group. Our findings highlight a pragmatic approach to AI integration that requires no model training, using structure and prompts to shape behavior. We position AI tutors not as teacher replacements but as enabling tools that extend feedback access, foster inquiry, and support what schools do best: help students learn.