Prompting Generative AI to Help You Plan for Your Class Quickly

A good teaching assistant (TA) can make a real difference. A TA needs clear direction to grade an essay against the same criteria you would use, and having someone to help carry the teaching load is invaluable. Generative AI can play a similar role. It doesn't only pressure you to redesign your assessments for academic-integrity reasons; with good prompting, it can help you do that redesign. What it needs from you is the same direction and oversight you would give a TA. 

Learning to prompt can save you time

Prompting AI means giving it specific parameters for what you want. When you start a conversation, you are signaling context, which helps it respond more usefully. As with a TA, well-defined expectations produce stronger results. Treat it as a cycle: you prompt, the AI responds, you refine, and so on, sharpening what you want by reacting to examples and asking for changes. A prompting structure that works well is: 

• Role: tell the AI to “think” like a particular person or discipline. 

• Task: summarize what the AI should do, e.g. make a test question about X topic. 

• Requirements: specify what should be included or left out. 

The AI keeps generating examples and you keep refining until you get what you want. Then you copy it into your document, Canvas quiz, and so on. 

Multiple types of assessments can be generated

Generative AI can draft multiple-choice questions for students to practise with or for instructors to use as assessment items, depending on the role and purpose you give it. It can even move those low-level, fact-based questions up Bloom's taxonomy to make them better tests of student mastery in seconds. The same works for assignments: tell it “you are a teacher,” give it your course outcomes, and ask it to draft an assignment of the type you want, then refine. The more specific you are about role, task, and requirements, the stronger the result, and the more efficient the process becomes as you practise. 

Prompting is an essential skill

Prompting is now an essential skill for knowledge workers and the academy. Knowing how to chat with generative AI is like knowing how to run a good internet or database search, but even more important. As you use AI to offload some of the thinking or typing, remember that every career we prepare students for is undergoing its own AI shift. Asking an AI to do some of the thinking for you is a form of cognitive offloading, and a good prompt is how you access it, much as you already offload by using a calculator, setting a timer by voice, or adding a meeting to a digital calendar. 

Watch for other articles on modifying courses in light of cognitive offloading, and on designing activities so students don't offload the key skills they need to build. 

Further information:

Try ALDA (USask NSID login), the USask-built tool that helps write course outcomes and syllabi and offers EDI suggestions. Read about ALDA in the LTE Toolkit. 

Review the USask educator guidelines for AI and the broader AI at USask hub. 

^{Title image credit: Tumisu from Pixabay}

This resource is shared by the Gwenna Moss Centre for Teaching and Learning (GMCTL), University of Saskatchewan, under a CC BY-NC-SA license.