Beyond AI Delegation: A Prompt Pattern Framework for Productive Struggle and Evaluative Judgement in Secure Coding Education

2026-05-23

AI Summary

This study addresses the risk that students’ overreliance on large language models (LLMs) for programming tasks may circumvent deep cognitive engagement, thereby undermining durable understanding and secure coding competencies. Grounded in design science research and integrated with the DELTA instructional framework, this work proposes a novel prompting framework that systematically maps prompt engineering to two core pedagogical constructs: “productive struggle” and “evaluative judgment.” The framework comprises nine distinct prompting patterns—including Flipped Interaction, Alternative Approaches, and Cognitive Verifier—which were implemented in an advanced secure coding course. Empirical results demonstrate that the framework effectively sustains students’ cognitive engagement and active reasoning, supports the development of their judgment in vulnerability identification and remediation tasks, and offers a reproducible design paradigm with empirical grounding for AI-augmented instruction.

Abstract

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.

Problem

• AI delegation
• productive struggle
• evaluative judgement
• secure coding education
• cognitive engagement

Innovation

• Prompt Engineering Patterns
• Productive Struggle
• Evaluative Judgement
• AI-Augmented Learning
• Secure Coding Education