Have students craft physically detailed prompts as a form of experimental design before measuring AI-generated scenarios¶

Strategy · All strategies
Evidence · no claims cited

Description¶

A teaching activity in which students write text prompts specifying the visual and physical characteristics of a scenario — without embedding the equations of motion — then track and validate the resulting video against analytical models. The article recommends this because "Crafting a prompt is thus itself a form of experimental design, one that encourages students to think carefully about the physical parameters that define a scenario before attempting to measure anything." It engages students in designing prompts, tracking motion, and fitting physical models rather than passively observing.

Design Implications¶

Context¶

Requirements¶

• Prompts must specify physical parameters (dimensions, masses, media, viewing perspective) while avoiding explicit implementation of the underlying equations of motion

Constraints¶

• Generated videos are not explicitly constrained by the dynamical laws, so recovered parameters are approximate rather than exact

Target Learners¶

• engineering undergraduates in introductory physics

Target Learning Goals¶

• experimental design
• quantitative validation
• connecting measurement to understanding

Related Strategies¶

• Simulations + Structured Activity

Examples¶

-

Key Sources¶

• Laura B. Alvarado-Cruz, Josep Ll. Suñer, Pedro Yuste, Juan C. Castro-Palacio, Juan A. Monsoriu, and Francisco M. Muñoz-Pérez. (2026). From Prompts to Physical Laws: A Generative AI Workflow for Engineering Physics Education. https://arxiv.org/abs/2609.19400