Designing AI-Enabled Engineering Courses: E-AIP Framework for Learning Outcomes, Process Evidence, and Integrity

Abstract

Artificial intelligence (AI) is entering engineering courses rapidly, yet tool-led adoption can weaken assessment validity and academic integrity. This paper presents the E-AIP (Engineering–AI Pedagogy) Framework, which centers three pillars learning Outcomes, Process Evidence, and Integrity & Ethics Guardrails and links them to design levers (AI function, task authenticity, feedback granularity, locus of agency). We define seven constructs, state eight propositions about alignment, validity moderation, authenticity, and agency, and operationalize E-AIP through a compact matrix (AI function × outcome type with required process evidence and guardrails). Two design patterns (CS1 debug-with-defense; circuits param-twins) illustrate classroom use; a lightweight adoption toolkit (two rubrics and an integrity or privacy checklist) supports immediate deployment. Additional patterns and full matrices appear in the online supplement. E-AIP enables instructors to capture AI’s benefits while preserving what scores validly claim to measure.

Ähnliche Arbeiten