Lessons Learned from Integrating Generative AI into an Introductory Undergraduate Astronomy Course at Harvard

Christopher W. Stubbs; Dongpeng Huang; Jungyoon Koh; Madeleine Woods; Andrés A. Plazas Malagón

Lessons Learned from Integrating Generative AI into an Introductory Undergraduate Astronomy Course at Harvard

Physics Education 2026-02-05 v1 Instrumentation and Methods for Astrophysics

Authors: Christopher W. Stubbs , Dongpeng Huang , Jungyoon Koh , Madeleine Woods , Andrés A. Plazas Malagón

Abstract

We describe our efforts to fully integrate generative artificial intelligence (GAI) into an introductory undergraduate astronomy course. Ordered by student perception of utility, GAI was used in instructional Python notebooks, in a subset of assignments, for student presentation preparations, and as a participant (in conjunction with a RAG-encoded textbook) in a course Slack channel. Assignments were divided into GAI-encouraged and GAI-discouraged. We incentivized student mastery of the material through midterm and final exams in which electronics were not allowed. Student evaluations of the course showed no reduction compared to the non-GAI version from the previous year.

Keywords

Generative AI Astronomy Education Course Integration Student Evaluation RAG-encoded Textbook

Cite

@article{arxiv.2602.04389,
  title  = {Lessons Learned from Integrating Generative AI into an Introductory Undergraduate Astronomy Course at Harvard},
  author = {Christopher W. Stubbs and Dongpeng Huang and Jungyoon Koh and Madeleine Woods and Andrés A. Plazas Malagón},
  journal= {arXiv preprint arXiv:2602.04389},
  year   = {2026}
}

Comments

27 pages, submitted to the Journal of Astronomy and Earth Sciences Education

Lessons Learned from Integrating Generative AI into an Introductory Undergraduate Astronomy Course at Harvard

Abstract

Keywords

Cite

Comments

Related papers