As we stand on the edge of AI-driven educational transformation, mastering prompt adaptation paves the way for a future where personalized learning, data-driven insights, and enhanced engagement will be the norm. The ripple effect of this knowledge promises a major shift in how we perceive and interact with AI in education.
Hopkins, 2023
Overview
As workplaces start seeing the benefits of generative artificial intelligence (GenAI) tools for productivity, proficiency, and creativity, higher education can play a key role in helping students develop the necessary skills for the successful and responsible use of GenAI (Keyhani et al, 2023). Course instructors can guide their students further towards AI literacy, which is essential for future professionals across diverse disciplines.
Purpose: This resource aims to provide educators with practical strategies on how to help students learn to effectively write GenAI prompts and therefore, develop essential GenAI competencies.
Key terms
Generative Artificial Intelligence (GenAI) refers to machine learning models that generate coherent content. They typically do this by training a “neural network” on vast amounts of previously existing content.
In the context of generative AI, prompting is the process of instructing AI or, more precisely, it is the skill and practice of writing inputs (“prompts”) for generative models. According to Oppenlaender et al. (2023, p. 1), “prompt engineering is iterative and interactive — a dialogue between humans and AI in an act of co-creation.”
Effective prompt writing supports instructors in designing authentic GenAI-assisted activities and assessments. Learning how to prompt well also provides students with opportunities to develop future-focused skills that they can use during their educational journey and once they enter the workforce.
Although some generative AI models are capable of receiving images and video input, in this resource, we will concentrate on text prompts.
There are multiple tools built using Generative AI models. For the purposes of this resource, we used the ChatGPT 3.5 tool to provide examples of effective prompts.
![AI image](/sites/default/files/styles/ucws_image_desktop/public/2024-05/uuuuu.png?itok=kFKr1WfZ)
How course instructors can guide students towards AI literacy
Not all students will know instinctively how to use AI tools. Multiple studies have suggested that students are not “digital natives” who grew up in the digital age and are by default tech-savvy (Janschitz & Penker, 2022; Eynon, 2023; Scolari, 2019; Kirschner, & De Bruyckere, 2017; Selwyn, 2009).
Consider the following steps when preparing students for the use of GenAI in your courses:
- Include a statement on the use of GenAI in your course outline;
- Explain to your students the benefits and limitations of GenAI tools for learning;
- Explain to your students how to write effective GenAI prompts;
- Provide examples of good prompts;
- Provide prompt templates for your assignment to students; and
- Share resources and useful links on the use of GenAI in education.
Enhancing skills development through effective prompt writing
“Teaching students about AI is essential for developing their digital literacy, and critical thinking skills, and preparing them for future academic and career success” (Bojorquez & Vega, 2023).
Students learn best through doing, and guiding students to learn how to write effective prompts will support them in learning the skills they need for a successful future. Regardless of the discipline, modelling effective prompt writing may demonstrate the essential skills that students can develop while using GenAI.
Crafting effective prompts is a catalyst for honing essential skills, such as critical thinking, knowledge application, analysis, interdisciplinary exploration, prompt research and synthesis, communication and collaboration skills.
Guiding principles of writing effective prompts for GenAI
Lo (2023) discusses five elements of the CLEAR framework which could be adapted for writing effective prompts for GenAI. The CLEAR framework can be used as a “scaffold for devising effective prompts for AI language models, combining precision and creativity, science, and art” (Lo, 2023, p. 208).
CLEAR stands for:
Clear Logical Explicit Adaptive Reflective
![Text reads "C"](/sites/default/files/styles/ucws_image_desktop/public/2024-05/1_4.png?itok=j_aQbJHi)
Concise
Clear and precise prompts guide the AI model’s understanding leading to a more relevant response.
Initial Prompt | Improved Prompt |
"Explain the universe." | "Provide an overview of the Big Bang theory and its significance in understanding the origin and expansion of the universe." |
Note: Limiting each prompt to one request or question is recommended so as not to overwhelm the tool. Remember it is still just a machine!
![Text reads "L"](/sites/default/files/styles/ucws_image_desktop/public/2024-05/2_1.png?itok=M737B5hq)
Logical
Providing context within prompts helps the AI model create meaningful generated output.
Initial prompt | Improved prompt |
“Tell me about programming” | “Explain the concept of loops in programming languages and their importance in executing repetitive tasks” |
Note: To provide context, try defining the role you would like the AI tool to assume or describe your role or level of knowledge. For example:
- You are a first-year student of computer science.
- Act as an expert in programming languages.
- Assume I am 10 years old.
- Explain the concept of loops in programming languages.
![Text reads "E"](/sites/default/files/styles/ucws_image_desktop/public/2024-05/3_1.png?itok=qhCuEaM6)
Explicit
Including a specific structure or style in your prompt, may assist the AI model in meeting user expectations in terms of the format and length of the generated responses.
Initial Prompt | Improved Prompt |
“What are the causes of climate change?” | “List and explain in 10 sentences, the primary human-induced factors contributing to climate change, including the impact of carbon emissions and deforestation? Use lay terms”. |
Note: To help you get more accurate results, consider specifying the following in your prompts:
- Background information related to the topic (what AI can base its response on)
- Length of response (number of sentences, paragraphs, words, or characters)
- Format (a list, paragraph, chart)
- Structure (essay, blog post, poem)
- Style (formal or informal)
- Target audience (who this is intended for)
- Examples (provide an example of what you are looking for) (Workiva, 2023)
Westling (2023) sums up these details into the following AI prompt formula: [Deliverable specifics] + [Voice] + [Objective] + [Ideal format]
![Text reads "A"](/sites/default/files/styles/ucws_image_desktop/public/2024-05/4_0.png?itok=HXtprX_9)
Adaptive
Experiment with general and then more specific questions or statements to assist the Al model in generating a response that matches the desired output.
Initial Prompt | Improved Prompt |
“How does technology affect society?” | “Discuss both the positive and negative impacts of technology on various aspects of society, including education, healthcare, and social interactions.” |
![Text reads "R"](/sites/default/files/styles/ucws_image_desktop/public/2024-05/5_0.png?itok=VX6L66Wr)
Reflective
Evaluate and improve the accuracy, coherence, and utility of the generated responses. For example, after receiving a final set of responses, tally how many, what kind, and how the prompts were adapted to achieve the desired result
Initial prompt | Improved prompt |
Any | Identify what could be refined in your prompt and try again. - Rephrase your initial prompt. - Give AI more information. - Change your approach. |
Note: Use the “chain of thought” technique to increase response accuracy, e.g. by using prompts like “Work on this problem step-by-step” or “Are you sure?” (Chen et al, 2023).
Meta-prompting
Another technique to improve your prompt writing is by using meta-prompting techniques, which can help students determine what they need to learn when they are not sure.
For example: "I want to learn about computer programming, but I don't know where to start. Can you ask some questions to help you figure out where I need to start and what questions I need to ask first?"
To learn more: Meta-Prompting Concept
Introducing prompt templates to students
To guide students in their use of GenAI tools, consider providing them with a prompt template that they can use.
Prompt templates are “pre-defined structures or formats that can be filled with specific content, allowing for efficient generation of new prompts” (Maynard, 2023). Instructors may create prompt templates for their students to lead them in their interaction with a GenAI tool.
Here is an example of a prompt template: ChatGPT Prompt Template for a French Grammar Class
Prompt templates can be provided at the beginning of the class/semester as an example of how students may lead their “conversation” with GenAI. Gradually, as you help students improve their prompt-generation skills, they may start creating prompts for further assignments on their own.
Prompt templates are reusable and can be repurposed for different classes and activities. On AI platforms, such as ChatGPT, prompts are saved in chats, so the same template can be viewed and copied into new chats.
More information
Some applications may also help you and your students with prompt templates:
Discipline-specific examples of effective prompt writing
Example: Sociology
Prompt: You are a student in a Sociology 101 class. Create a 3-part outline for a 300-word essay on the harm of TV commercials on children's channels.
Example: English
Prompt: List five synonyms of the word “work”, explain the difference between them and provide examples of sentences with their use.
Example: Mathematics and science
- Explanations and examples
Prompt: Act as a tutor to a first-year student of math. Explain what a vector function is in lay terms in 2 paragraphs and provide 3 examples.
- Problem-solving assistance
Prompt: A rectangle has a width of 19 cm and a length three times greater than its width. Why is it wrong that its perimeter is 76 cm? Explain step by step.
- History simulations (Breen, 2023)
Prompt: You are a city councilor in a medieval Italian city-state, negotiating a civic response to the plague. Simulate a conversation with your subordinates when you arrive at work.
More: Simulating History with ChatGPT (Breen, 2023)
- Researching sociological concepts
Prompt: I am a sociologist researching the societal consequences of Generative AI. What should my areas of focus be?
More: A Sociological Conversation with ChatGPT about AI Ethics, Affect and Reflexivity (Balmer, 2023)
Example: Computer science
- Exploring libraries
Prompt: List 5 open-sourced AI libraries that I can use to generate a summary of the main core contents of any web page, ignoring any ads or embedded materials (Based on: How to Use ChatGPT To Wrote Code).
- Reviewing and debugging code
Prompt: Here’s a Python code snippet. The function is supposed to sort a list, but it’s not returning the expected output. Can you identify the problem and explain why it is wrong?
More: Top ChatGPT prompts for programmers with examples ; Mastering Coding Challenges with AI: A Comprehensive Guide to Using ChatGPT Prompts for Coding Tasks
Note: The responses for the given prompts were generated with the help of ChatGPT 3.5.
More on prompts for different disciplines:
Reflective questions
Crafting effective prompts is important for guiding students in the GenAI learning process. The following are a few reflective questions to consider based on the CLEAR framework (Lo, 2023) when guiding students to write effective prompts:
- Clarity: How do clear, precise prompts lead to more relevant AI-generated responses?
- Logical alignment: What role does contextual information within prompts play in creating meaningful AI outputs?
- Explicitness: In what ways does structuring prompts with specific styles result in user expectations for format and length?
- Adaptability: How can the combination of general and specific prompts lead to enhanced AI-generated responses?
- Reflection: Which methods enable the evaluation and enhancement of accuracy, coherence, and usefulness in AI-generated responses?
Conclusion
This resource is a starting point for conversations between instructors and students as they begin to use GenAI in their courses. Learning how to write effective GenAI prompts may help students to gain a deeper understanding of course material as they enhance their understanding through clearer more explicit prompts. The more comfortable and experienced students become with prompt writing, the more successful they may be in their courses as they develop key skills needed for their future careers.
![Brain connected to computer](/sites/default/files/styles/ucws_image_desktop/public/2024-05/uuuuu%20%281%29.png?itok=OqFnngbp)
References
Balmer, A. (2023). A Sociological Conversation with ChatGPT about AI Ethics, Affect and Reflexivity. Sociology, 57(5), 1249-1258. https://doi.org/10.1177/00380385231169676
Breen, B. (2023, Sept 12). Simulating history with ChatGPT: The case for LLMs as hallucination engines. Res Obscura. https://resobscura.substack.com/p/simulating-history-with-chatgpt
Bojorquez, H., & Vega, M. M. (2023, May 31). The importance of Artificial Intelligence in education for all students. Intercultural Development Research Association. https://www.idra.org/resource-center/the-importance-of-artificial-intelligence-in-education-for-all-students/
CESE NSW What Works Best in Practice (2023). A Teacher’s Prompt Guide to ChatGPT. https://usergeneratededucation.files.wordpress.com/2023/01/a-teachers-prompt-guide-to-chatgpt-aligned-with-what-works-best.pdf
Chen, J., Chen, L., Huang, H., & Zhou, T. (2023). When do you need Chain-of-Thought Prompting for ChatGPT? https://doi.org/10.48550/arxiv.2304.03262
Chew, S.L. & Cerbin, W. J. (2021) The cognitive challenges of effective teaching, The Journal of Economic Education, 52(1), 17-40, https://doi.org/10.1080/00220485.2020.1845266
Crawford, J., Cowling, M., & Allen, K. (2023). Leadership is needed for ethical ChatGPT: Character, assessment, and learning using artificial intelligence (AI). Journal of University Teaching & Learning Practice, 20(3). https://doi.org/10.53761/1.20.3.02
Ekin, Sabit (2023). Prompt Engineering For ChatGPT: A Quick Guide To Techniques, Tips, And Best Practices. TechRxiv. Preprint. https://doi.org/10.36227/techrxiv.22683919.v2
Giray, L. (2023). Prompt Engineering with ChatGPT: A Guide for Academic Writers. Annals of Biomedical Engineering, 51(12), 2629–2633. https://doi.org/10.1007/s10439-023-03272-4
Gutiérrez, J. (2023) Guidelines for the Use of Artificial Intelligence in University Courses. Version 4.3, Universidad del Rosario. https://forogpp.files.wordpress.com/2023/02/guidelines-for-the-use-of-artificial-intelligence-in-university-courses-v4.3.pdf
Hart-Davis, G. (2023). Killer ChatGPT Prompts: Harness the Power of AI for Success and Profit (1st ed.). John Wiley & Sons, Incorporated.
Hopkins, D. (2023, Nov 7). Education & Leadership. Prompts. https://www.dontwasteyourtime.co.uk/ai/prompts-5/
Huang, J. (2023). Engineering ChatGPT Prompts for EFL Writing Classes. International Journal of TESOL Studies, 5(4), 73-79. https://doi.org/10.58304/ijts.20230405
Keyhani, M., Hemmati, H., & Saldago, L. (2023, Nov 21). Why student experiments with Generative AI matter for our collective learning. The Conversation. https://theconversation.com/why-student-experiments-with-generative-ai-matter-for-our-collective-learning-210844
Korzynski, P., Mazurek, G., Krzypkowska, P., & Kurasinski, A. (2023). Artificial intelligence prompt engineering as a new digital competence: Analysis of generative AI technologies such as ChatGPT. Entrepreneurial Business and Economics Review, 11(3), 25–37. https://doi.org/10.15678/EBER.2023.110302
Lee, U., Jung, H., Jeon, Y., Sohn, Y., Hwang, W., Moon, J., & Kim, H. (2023). Few-shot is enough: exploring ChatGPT prompt engineering method for automatic question generation in English education. Education and Information Technologies. https://doi.org/10.1007/s10639-023-12249-8
Lo, L. S. (2023). The Art and Science of Prompt Engineering: A New Literacy in the Information Age. Internet Reference Services Quarterly, 27(4),203-210. https://doi.org/10.1080/10875301.2023.2227621
Maynard, A. (2023). Developing and using prompt templates with ChatGPT. https://andrewmaynard.net/prompt-templates/
NSW Government Education (2023). Guidelines regarding use of generative AI (ChatGPT). Education for a Changing World. https://education.nsw.gov.au/teaching-and-learning/education-for-a-changing-world/guidelines-regarding-use-of-generative-ai-chatgpt#Use3
Oppenlaender, J., Linder, R., & Silvennoinen, J. (2023). Prompting AI art: An investigation into the creative skill of prompt engineering. arXiv.Org. https://doi.org/10.48550/arxiv.2303.13534
Oppenlaender, J., Visuri, A., Paananen, V., Linder, R., & Silvennoinen, J. (2023). Text-to-Image Generation: Perceptions and Realities. https://doi.org/10.48550/arxiv.2303.13530
Rouhiainen, L. (2019, Oct 14). How AI and Data Could Personalize Higher Education. Harvard Business Review. https://hbr.org/2019/10/how-ai-and-data-could-personalize-higher-education
Short, C. E., & Short, J. C. (2023). The artificially intelligent entrepreneur: ChatGPT, prompt engineering, and entrepreneurial rhetoric creation. Journal of Business Venturing Insights, 19, e00388-. https://doi.org/10.1016/j.jbvi.2023.e00388
Westling, M. (2023). 5 Strategies for Teaching AI Literacy to Students. Course Hero. https://facultyclub.coursehero.com/teaching-with-technology/5-strategies-for-teaching-ai-literacy-to-students/