Using generative AI is like having a discussion with a colleague or advisor. To be effective, you need to provide your context, the topic about which you are curious, and the ideal format for the response. This page provides resources for Ohio State instructors and is referred to during many of our interactive workshops. It contains background information about AI, Ohio State resources as well as resources from a variety of sources.
Workshop Materials
- Sample course design prompts
- AI-SPARC Handout
- AI-TiLT Template
- Presentation and recording are available upon request
- Workshop recordings are intended for participants to review. Please direct any additional requests for access to the Drake Institute (drakeinstitute@osu.edu)
Prompt Components (TRACI)
TRACI is one kind of prompting framework that is useful for engineering prompts of Generative AI. The letters refer to various components of a prompt:
T-Task: Task refers to the type of output the prompt should achieve. For example a rubric, learning goals or a syllabus statement.
R-Role: Role refers to the persona generative AI should take on when responding. For example, an expert educator, a student advisor and instructional designer
A-Audience: Audience refers to the group to whom the response is written. For example, introductory biology students, graduate-level competitive study majors, doctor of pharmacy students.
C-Create: Create refers to the format of the output. For example, 200 words, a three-column table or an acrostic poem.
I-Intent: Intent communicates the purpose of the response. For example, to promote a growth mindset or clearly communicate expectations.
Considering the TRACI model will improve initial prompts and provide guidance as prompts are revised.
Resources
Ohio State University resources
- Artificial Intelligence at Ohio State (ai.osu.edu)
- Teaching and Learning Resource Center -
- Drake Institute
- Office of Academic Affairs - Artificial intelligence and academic integrity
- Office of Digital Technology Innovation Aye, Aye, A.I.!
- Committee on Academic Misconduct
- COAM Instructor Resources
- Don’t Fall Victim to Clickthrough Agreements: Use Supported Tools Instead
Additional resources
- Bowen, J.A. and Watson, C.E. (2024) Teaching with AI : A Practical Guide to a New Era of Human Learning. Baltimore, MD: Johns Hopkins University Press.
- How to Cite AI-Generated Content Purdue University
- Ithaka S+R Generative AI Product Tracker
- The Learning with AI initiative from the University of Maine (umaine.edu)
- Lesson planning with AI: Save time and get ideas
- Microsoft Copilot
- Prompt Engineering Guide
- Prompt-ingredients-one-pager.pdf (microsoft.com)
- Wharton Interactive Crash Course: Practical AI for Instructors and Students — YouTube
- Prompt Library — AI for Education
- User’s Guide to the TRACI Prompt Framework for ChatGPT
- 7 Things You Should Know About Generative AI | EDUCAUSE Review
References
- Abedi, M.; Alshybani, I.; Shahadat, M.R.B.; Murillo, M., 2023. Beyond Traditional Teaching: The Potential of Large Language Models and Chatbots in Graduate Engineering Education. Qeios. 2023.
- Giray, L. Prompt Engineering with ChatGPT: A Guide for Academic Writers. Ann Biomed Eng., 2023, 1-5.
- Kıyak, Y. S., & Emekli, E. (2024). ChatGPT prompts for generating multiple-choice questions in medical education and evidence on their validity: a literature review. Postgraduate medical journal, qgae065. Advance online publication. https://doi.org/10.1093/postmj/qgae065
- Meskó, B. Prompt engineering as an important emerging skill for medical professionals: tutorial. J. Med. Internet Res, 2023, 25, e50638.
- Mollick, E.,Assigning AI: Seven Ways of Using AI in Class (oneusefulthing.org)
- Mollick, E., A guide to prompting AI (for what it is worth) One useful thing
- White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J. and Schmidt, D.C., 2023. A prompt pattern catalog to enhance prompt engineering with chatgpt arXiv preprint arXiv:2302.11382.\
- Zamfirescu-Pereira, J.D.; Wong, R.Y.; Hartmann, B.; Yang, Q. 2023, April. Why Johnny can’t prompt: how non-AI experts try (and fail) to design LLM prompts. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, 2023, 1-21