AI-supported exploration assignment in an asynchronous introductory physics course¶

Design · All designs
Evidence · 1 claim (1 for) · 1 study (1 design), q1 · 0 of 1 report an effect size · 1 claim rests on one study

Description¶

The article describes an implemented assignment in which students in an asynchronous introductory physics course, Patterns of Nature, with approximately 70 students, selected one or two subtopics, began an AI conversation with an instructor-provided context prompt, engaged in sustained dialogue with follow-up exchanges, and submitted the full transcript for credit. Full credit was tied to evidence of genuine dialogue rather than isolated question asking. A rubric emphasized prompt quality, engagement, learning depth, and organization.

Design Implications¶

Context¶

Requirements¶

Students must begin with the context prompt and sustain the interaction through multiple meaningful follow-up exchanges

Constraints¶

Some students asked many questions but did not fully engage with the AI's responses and follow-up prompts

Target Learners¶

introductory university physics students in an asynchronous course

Learning Goals¶

exploring physics concepts in depth and connecting content to personal interests

Claims¶

AI exploration assignments helped students connect physics content to their personal lives and interests [+W]

Examples¶

-

Key Sources¶

Miguel Rodriguez and Peter Wulff. (2026). Artificial Intelligence Driven Physics Assignments using Context Prompts. https://arxiv.org/abs/2609.22578

Page metadata

Field	Value
`type`	`design`
`id`	`ai-exploration-assignment-patterns-of-nature`
`title`	`AI-supported exploration assignment in an asynchronous introductory physics course`
`description`	`The article describes an implemented assignment in which students in an asynchronous introductory physics course, Patterns of Nature, with approximately 70 students, selected one or two subtopics, began an AI conversa...`
`status`	`review`
`generated`	by `process:settle-candidates` on `2026-10-10`
`trust`	unverified — no one has confirmed this page's content
`sources`	1 — `miguel-rodriguez-and-peter-wulff-2026`

Frontmatter is the page's machine-readable record — see the Schema & Guide.