Towards SocratiCode: Designing a Generative AI-Based Programming Tutor for K-12 Students through a 4-Week Participatory Design Study

2026-05-18

AI Summary

This study addresses the limitations of existing generative AI programming tutoring systems, which often overwhelm K–12 novices with overly directive interactions that induce cognitive overload. To mitigate this, the authors conducted a four-week participatory design process with two students to iteratively develop SocratiCode—a system that reconfigures generative AI from an “answer engine” into a Socratic, adaptive learning partner. SocratiCode emphasizes guided questioning, reflective prompts, misconception detection, progressive hinting, and enforced wait times to scaffold learning. By embedding AI within a human-centered instructional framework, this approach innovatively aligns AI support with the cognitive rhythms and developmental needs of young learners. Preliminary findings indicate that the system significantly enhances explanation clarity, increases student engagement in problem solving, and better supports the learning trajectories of K–12 programming beginners.

Abstract

Generative AI creates new opportunities for programming education, but many existing systems remain overly directive, producing lengthy explanations and premature solutions that can overwhelm K-12 novices. In this paper, we present a participatory design study of how an adaptive tutorial system, SocratiCode, evolved toward a Socratic tutoring model for beginner programming instruction. Drawing on weekly learner feedback, we iteratively refined the system over a four-week study with two K-12 students learning Python. Across iterations, the system shifted from flexible tutorial generation toward a more dialogic form of support characterized by guided questioning, reflection prompts, misconception checks, incremental hints, and mandatory pauses for learner input. Our preliminary observations suggest that this Socratic shift improved explanation clarity, supported problem-solving engagement, and better aligned instruction with novice learners' needs, especially when combined with human guidance. We argue that generative AI in K-12 programming education may be most effective not as an answer engine, but as a Socratic, adaptive learning companion embedded within a human-guided instructional framework.

Problem

• generative AI
• programming education
• K-12 students
• Socratic tutoring
• adaptive learning

Innovation

• Socratic tutoring
• generative AI
• participatory design
• adaptive learning companion
• K-12 programming education