Artificial Intelligence

A prompt is the set of instructions you give to a large language model (LLM) such as ChatGPT to perform a specific task and generate an output. These instructions can range from a few words to multiple sentences or even several paragraphs. The more detailed, clear, and structured your instructions are, the more likely the AI will produce a useful, relevant, and accurate result.

Prompting is not a one-time or static action: it’s a skill that develops over time with practice. Each interaction with an AI tool is different because your query, the context, and the desired output all vary. Even a small change in wording or additional detail can lead to a different result. Over time, you’ll learn how to adjust your prompts to suit your goals, your audience, and the specific task at hand.

It’s also worth noting that the same prompt may produce different outputs in different AI models. Trying your query in multiple tools, such as ChatGPT, Claude, Gemini, or Copilot, can give you varied perspectives, styles, and levels of detail. This is especially valuable for academic work, where comparing outputs can reveal gaps, biases, or new insights.

When you interact with an AI tool, every question, request, or piece of background information you provide is part of your prompt. A well-crafted prompt can significantly improve the quality of the output, your satisfaction with the answer, and the AI’s ability to handle complex or nuanced tasks.

Tips for Better Prompts

• Include clear instructions (what you want it to do).
• Provide context (background information, audience, format, tone).
• Specify constraints (word count, citation style, perspective).
• Use follow-up prompts to refine or expand results.
• Experiment—try rephrasing, adding details, or testing in different AI tools.

Common Tasks for Large Language Models
Generative AI tools can perform a wide variety of tasks across academic, professional, and creative contexts, including:

• Text generation: drafting essays, blog posts, abstracts, or research overviews.
• Image generation: creating visuals from text descriptions.
• Question answering: explaining concepts, clarifying terms, or providing definitions.
• Problem-solving: working through logic puzzles, mathematical problems, or scenario planning.
• Code writing: generating, debugging, or explaining code.
• Data analysis: summarizing datasets, finding trends, or formatting results.
• Text summarization and synthesis: condensing readings or combining information from multiple sources.
• Language translation: translating text between languages while preserving meaning and tone.

By developing strong prompting skills through experimentation, iteration, and cross-model comparison, you can make AI tools work more effectively for your studies, research, and creative projects, turning them into reliable collaborators rather than unpredictable guessers.

The CLEAR framework, created by Librarian Leo S. Lo at the University of New Mexico, is a framework to optimize prompts given to generative AI tools. To follow the CLEAR framework, prompts must be: 

Concise: "brevity and clarity in prompts"

• This means to remain specific in your prompt. 

Logical: "structured and coherent prompts" 

• Maintain a logical flow and order of ideas within your prompt.

Explicit: "clear output specifications"

•  Provide the AI tool with precise instructions on your desired output format, content, or scope to receive a stronger answer. 

Adaptive: "flexibility and customization in prompts"

• Experiment with various prompt formulations and phrasing to attempt different ways of framing an issue to see new answers from the generative AI 

Reflective: "continuous evaluation and improvement of prompts" 

• Adjust and improve your approach and prompt to the AI tool by evaluating the performance of the AI based on your own assessments of the answers it gives. 

This information comes from the following article. It is highly encouraged to read through this article if you would like to improve your prompt writing. 

Lo, L. S. (2023). The CLEAR path: A framework for enhancing information literacy through prompt engineering. The Journal of Academic Librarianship, 49(4), 102720–. https://doi.org/10.1016/j.acalib.2023.102720 
University of Calgary Access Permalink here

Effective prompts combine clear instructions, relevant context, and iterative refinement. Use these strategies to guide generative AI toward producing accurate, relevant, and useful outputs. Instruction and context work well when used together. Prompting generative AI to give you the best output takes trial and error, so reword your prompt a few ways to see what generates the best response. 

1. Instruction

Tell the AI exactly what you want it to do. Be explicit about the task and the process.
Examples of instructions:

• Think step-by-step
• Rephrase an idea
• Summarize an idea
• Synthesize two or more ideas

User Example:

• I am preparing an undergraduate paper on biofuels vs fossil fuels for my electrical engineering class. Develop a list of key arguments on the positives of biofuels and the positives of fossil fuels with citations.

2. Context

Explain your role, the AI’s role, and the purpose or audience for the task. This helps the AI produce a better-targeted output.

User Example:

• I am an undergraduate student preparing a presentation on biofuels for my energy & engineering class. Provide me a step-by-step guide to getting started.

Tip: Instruction and context work best together. Try rewording your prompt in a few ways to see which produces the strongest results.

3. Explain & Check

Before the AI starts, explain your topic or question and confirm it understands.

User Example:

• Do not start writing yet. Do you understand?

4. Clarifying Questions

Ask the AI to request more details before answering.

User Example:

• Please ask me all the questions you need to understand my prompt.

5. Tone and Direction

Guide the AI’s style, tone, and format.

User Examples:

• Write a 250-word summary in an academic tone about the connection between biodiesel and crop waste.
• Take the key points from the previous answer and rewrite them in a professional tone.
• Synthesize this article and simplify the arguments to a grade 12 reading level.

6. Provide Examples

Share sample outputs, keywords, or reference texts.

User Example:

Find more articles published between 2005–2020 like this: Demirbas, A. (2008). Biofuels sources, biofuel policy, biofuel economy and global biofuel projections. Energy Conversion and Management, 49(8), 2106–2116. https://doi.org/10.1016/j.enconman.2008.02.020.

7. Act as an Expert

Ask the AI to adopt an expert role and guide your learning process.

User Examples:

I am conducting a narrative review on Mitral Valve Repair vs. Replacement. Act as an expert and advise me on how to approach each step. Guide me through the concept of “X” in [subject] using an example.

Other Prompting Tips

• Break large topics into smaller steps or into smaller questions and ask the generative AI step by step. 
• Start a new chat for each unrelated topic so the AI works with a clean slate.
• You can also instruct the AI to ignore previous context in a conversation.
• Explore preloaded prompts from browser extensions or AI plugins.
• Paste your research question into the AI for feedback, step-by-step research planning, or counterarguments to your premise

Effective Prompt Wording for University Students

When working with generative AI for assignments, research, or skill-building, clarity is your best ally. The more specific and well-structured your request, the better the results you’ll get. Use the following phrasing ideas to make your prompts precise, academic, and purpose-driven.

Suggested Wording for Performing Specific Tasks

Action Verbs for Generating or Processing Content

• Write / Explain / Summarize / Compose
• Provide / Analyze / Compare and Contrast
• Rephrase / Rewrite / Reword
• Expand on (or “Elaborate on”)
• Create (e.g., “Create an outline,” “Create an image,” “Create a script”)

Phrasing for Asking Specific Questions

• Who / What / When / Where / Why / Whose / Which
• How did… (e.g., “How did X influence Y?”)
• How to… (e.g., “How to improve team communication?”)

Ways to Include Specific Contexts or Parameters

• “Write in an academic tone, approximately 500 words.”
• “Explain how to… in a professional setting.”
• “Describe the process from a beginner’s perspective.”
• “Provide examples relevant to [specific field or audience]. 

By combining an action verb, a clear question, and specific context, you give the AI everything it needs to produce relevant, higher-quality responses.