Prompt Engineering

Josh Anthony
Gonzaga University

The basic mechanics of this activity are simple: choose a reading from class and try to manipulate the LLM to recreate it as close to the original as possible. As a rule, I generally try to produce and run activities that are modular, interchangeable, and adaptable. This activity is no different. In one course, we used the prompt and only the prompt—no scaffolding. In other courses, we scaffolded LLMs, understood how prompt engineering might work, and worked as a class to construct the prompt we thought would produce a suitable outcome. 

For students, the limitations of the LLMs become clear almost immediately. With non-scaffolded classes, students will often attempt to put in the name of a text and instruct the LLM to recreate it—often to some hilarious results. Even with the scaffolded and carefully crafted prompts students begin to recognize the limitations. This might come in the form of length, depth, or even understanding of an abstract concept.

The most unexpected outcome was how deeply the students had to re-engage with content from the class. Of course, we have had discussions about voice, style, tone, message, etc. But, in this case, they felt compelled to clearly articulate these ideas to the LLM.

Emily Dux Speltz and Abram Anders
Iowa State University

This assignment is designed to enhance students' proficiency in advanced AI prompting techniques. The primary goal is to transform students who are already familiar with basic AI tool usage into advanced users capable of employing complex prompts effectively. Overall, we have found the activity to be successful in encouraging students to experiment with various advanced prompting techniques in a risk-free setting, allowing them to identify the prompting methods that resonated most with them. 

Brian Gogan
Western Michigan University

This assignment offers students an exploratory space—literally, a tabular document accompanied by an iterative process—within which they can refine the rhetoric of structured prompts and experiment with prompt engineering. As students focus on discrete rhetorical concepts, honing prompts to yield more optimal results, they further explore the relationships between production and reception, intent and interpretation. The assignment may be adapted for use in a single class or iterated across a weeks-long portion of a course to allow for differentiated learning. Weeks after having completed their last Gen/ReGen Log, my students still reference this assignment. Some of my students—themselves, college or high school educators—report success using Gen/ReGen Logs with their own students.