Date
Publisher
arXiv
Large language models make it easy for students to delegate writing, analysis, and problem-solving to automated systems, bypassing the effortful engagement that produces lasting understanding. We introduce a practical framework that helps educators keep GenAI in the course without removing the cognitive demands that make it worthwhile. We apply Design Science Research (DSR) to synthesise and adapt a taxonomy of nine prompt engineering patterns from established catalogs in the computer science literature, mapped to two pedagogical constructs: Productive Struggle and Evaluative Judgement. A course design for an Advanced Secure Coding module, structured using the DELTA framework, demonstrates the artifact's applicability. Nine prompt patterns, each mapped to a specific pedagogical function, give instructors fine-grained control over how students interact with AI. The secure coding design shows how three patterns (Flipped Interaction, Alternative Approaches, and Cognitive Verifier) scaffold vulnerability discovery and remediation while keeping students in the reasoning role. The framework provides a replicable approach to designing AI-augmented learning experiences that preserve student reasoning, and establishes a structured basis for future empirical evaluation in live course settings.
Study at a glance
- Question: How can prompt patterns be designed to preserve student reasoning and evaluative judgement in AI-assisted coding education?
- Setting and data: Master's-level research methods course at University of Applied Sciences St. Pölten, Austria; student numbers and years not stated.
- Method: Design Science Research (DSR) developing and demonstrating a pedagogical framework.
Why it matters
Generative AI lets students delegate thinking and problem-solving, bypassing the productive struggle needed for deep understanding. Educators need practical methods to integrate AI into courses without eliminating the cognitive demands that support learning.
Key findings
- A taxonomy of nine prompt patterns across four categories maps prompt engineering techniques directly to productive struggle and evaluative judgement.
- A secure coding course module design demonstrated how patterns like Flipped Interaction, Alternative Approaches, and Cognitive Verifier keep students in active reasoning roles.
- The multi-step assessment model uses student chat logs, comparative justifications, and refactored code to create learning activities resistant to academic dishonesty.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who age?
Why use AI?
Study design
