Date
Publisher
arXiv
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.
Study at a glance
- Question: How can an adaptive generative AI programming tutorial system evolve toward a Socratic tutoring model for K-12 beginners?
- Setting and data: Summer 2025 internship at a university; two 11th-grade high school students learning introductory Python over four weeks.
- Method: Participatory design study using daily and weekly surveys, reflections, and thematic analysis.
Why it matters
Many generative AI systems provide lengthy, directive answers that overwhelm K-12 novice programmers rather than supporting the reasoning processes, guided questioning, and reflection needed for durable understanding.
Key findings
- Preliminary observations suggest shifting toward Socratic guidance improved explanation clarity, supported active reasoning engagement, and better matched beginner students' developmental needs.
- Learners consistently preferred guided incremental hints and multiple problem-solving attempts over immediate, full code solutions.
- Human guidance remained essential alongside the AI tutor for addressing misconceptions, challenging weak reasoning, and explaining advanced programming topics.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Study design
