Michael V. Drake Institute for Teaching and Learning

Getting Started with Generative Artificial Intelligence: Considerations and Strategies

Developing prompts for use with generative AI is like planning to get advice from a knowledgeable colleague. To be effective, you need to provide your context, the topic about which you are curious, and the ideal format for the response. During this interactive workshop, you will learn about the form and function of AI prompts and practice developing prompts in a teaching and learning context. 

After this workshop, participants will be able to:

  • describe the general purpose and function of prompts (e.g., what they do and how they work)
  • list components of effective prompts 
  • evaluate prompts to aid in course design and assignment creation

Workshop Materials

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

Additional resources

References