Prompt-to-Primal Teaching

TL;DR

The paper addresses the risk of AI tools distorting novices' understanding in engineering education by proposing Prompt-to-Primal Teaching (P2P), a cyclical framework that combines student-generated prompts, data-driven instructor intervention, and grounding in first principles. Through four phases—Prompt, Data, Primal, and Reconciliation plus Repetition/Creation—P2P leverages AI as a catalyst for inquiry while ensuring rigorous validation against fundamental laws, thereby mitigating the illusion of understanding. A PMDC-based application illustrates how prompts guide exploration, data mining informs targeted instruction, and first-principles grounding anchors learning, with reflective practices and hand-written derivations reinforcing durable knowledge. Empirical results from two cohorts show increased engagement, higher-quality questions rooted in first principles, and a measurable midterm improvement, supporting the framework's potential to enhance AI literacy and engineering reasoning at scale.

Abstract

This paper introduces Prompt-to-Primal (P2P) Teaching, an AI-integrated instructional approach that links prompt-driven exploration with first-principles reasoning, guided and moderated by the instructor within the classroom setting. In P2P teaching, student-generated AI prompts serve as entry points for inquiry and initial discussions in class, while the instructor guides learners to validate, challenge, and reconstruct AI responses through fundamental physical and mathematical laws. The approach encourages self-reflective development, critical evaluation of AI outputs, and conceptual foundational knowledge of the core engineering principles. A large language model (LLM) can be a highly effective tool for those who already possess foundational knowledge of a subject; however, it may also mislead students who lack sufficient background in the subject matter. Results from two student cohorts across different semesters suggest the pedagogical effectiveness of the P2P teaching framework in enhancing both AI literacy and engineering reasoning.

Figures (5)

• Figure 1: Schematic representation of the Prompt-to-Primal (P2P) teaching framework, illustrating the cyclical integration of AI-based exploration, instructor-mediated analysis, first-principles grounding, and reflective repetition leading to creative application.
• Figure 2: Core dispositions (dimensions) contributing to learner efficacy in the formal educational context: (a) ideal situation when the student exhibit satisfactory levels of curiosity, engagement, and reflective openness; (b) a more realistic classroom with a diverse disposition.
• Figure 3: Schematic illustrating the pre-class activity where a student initiates an iterative dialogue with a Large Language Model (LLM) via self-generated prompts, which serves to foster the core learning disposition of Curiosity and generate exploratory data for the instructor.
• Figure 4: Phases 2 and 3 - Data and Primal (Promoting Engagement). Schematic demonstrating the synergistic role of Phase 2 (Instructor Data Processing and Mining) and Phase 3 (Classroom Grounding via First Principles) in the P2P framework.
• Figure 5: Phase 4 - Reconciliation, Repetition and Creation (Cultivating Reflective Openness). Schematic illustrating the final, student-driven phases of the P2P framework, where the learner critically reconciles AI-generated content with first-principles knowledge (4a), then consolidates and applies that knowledge to new creative tasks (4b).