Artificial Intelligence: a guide for students
Using AI at F&M
Consult with your professors regarding acceptable use of AI for your classes!
Also know F&M's Policies: F&M's Academic Honesty Policy and F&M's Student Code of Conduct
The CLEAR Framework
"In generative AI, a prompt is the input — such as text, an image, or instructions — given to an AI model to guide and shape the content it generates in response. When you provide this input, you’ll learn how to have conversations similar to human interactions and critique the results carefully. These back-and-forth exchanges with the AI model will produce the best results." --Elon University
The CLEAR Framework:
| Good | Needs Improvement | |
| Concise (also Clear) - Focus on the key words for the AI tool to analyze. Try to omit as many needless words* as possible. | Identify the top reasons undergraduate students attend Georgetown University. |
I am trying to figure out if I should be applying to Georgetown and if I would like it there. (The AI doesn't know you or your preferences, there are multiple "Georgetown" institutions, & are you applying to high school? Undergrad? Grad school?) |
|
Logical - Most AI tools look for relationships between words and concepts, so make sure your query presents concepts accurately and in their natural or logical order. If your question doesn’t make sense to you (or to someone else), it probably won’t make sense to the AI! |
Summarize the most promising vaccine candidates that protect against multiple strains of influenza. |
Can we make a flu vaccine organically? (Are you asking about a vaccine made with eggs obtained through organic farming? A vaccine developed through "organic" research? Something else?) |
| Explicit - Be clear in what you want from the AI. Giving the AI tool clear output directions can help the AI produce an answer that is useful to you. | Give me a concise summary of the major strengths and weaknesses of Georgetown University. |
What’s Georgetown University like? (What's your comparison for Georgetown? Do you want a short answer or a long one?) |
Even the best prompts may need improvement! The last two components address what to do after you’ve examined the AI’s answer to your initial prompt.
| Adaptive - Try a second prompt with keywords or topics suggested by the AI in its answer. If the AI tool has seeding or guidance settings, investigate different settings - do you get better results? If the tool allows you to specify words/concepts to exclude or ignore, can you refine your prompt by excluding concepts? |
Prompt 1: Why doesn’t Georgetown have a Metro station? Answer: (includes "geological obstacles") Prompt 2: What are the engineering challenges and geological obstacles to constructing a Metro station in Georgetown? |
|
Reflective - Always take a moment to reflect on the AI’s answer. Does it make intuitive sense to you? Does the answer refer to current research (if important for your query), or does it seem based on older research? Has the AI “hallucinated” or returned inaccurate information? Is the answer complete, or are there perspectives or voices unrepresented in the answer? You may need to craft additional prompts that specifically target gaps in the initial answer. |
Prompt 1: Give me a concise summary of the major strengths and weaknesses of Georgetown University. Prompt 2: Give me a concise summary of the major strengths and weaknesses of Georgetown University, from the perspective of a first-generation college student. |
Read more about the CLEAR framework in 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 Table adapted from "How to Craft Prompts - Artificial Intelligence (Generative) Resources" by Georgetown University under the Creative Commons Attribution NonCommercial 4.0 International License.
The PROMPT Framework
The PROMPT Framework is an easy way to remember the different factors that you can give a text generative AI to be more specific in prompting, depending on the context of your request. Access the PROMPT Worksheet and larger sized graphic.
The Four Pillars of a Perfect AI Prompt
The Four Pillars of a Perfect AI Prompt
1. Defining the Goal: Clarity is Key. The first and most crucial step in writing an AI prompt is to be specific about your objective. AI thrives on clarity—vague requests lead to vague answers.
Example Request (Too Vague):
❌ "Tell me about coffee."
>This could lead to an overwhelming amount of generic information.
Instead, make your goal clear:
✅ "I want a comparison of Arabica and Robusta coffee beans, highlighting their taste, caffeine content, and best brewing methods."
>A well-defined goal ensures that the AI filters out unnecessary details and provides a focused, relevant response.
2. Specifying the Return Format: Get Responses the Way You Want. AI can present information in various ways—paragraphs, bullet points, tables, or even code snippets. If you don’t specify, you might receive an answer that doesn’t match your needs.
Example Request Without Format:
❌ "Compare Arabica and Robusta coffee beans."
>This might result in a long, unstructured response.
Instead, define the format:
✅ "Provide the comparison in a table format with three columns: Coffee Bean Type, Key Characteristics, and Recommended Brewing Method."
>By structuring your request, you save time and receive well-organised information.
3. Adding Warnings: Improve Response Accuracy. AI can sometimes generate outdated, misleading, or incomplete responses. Adding warnings helps refine accuracy and credibility.
Example Request Without Warnings:
❌ "List the top coffee-growing countries."
>This may provide a general list without current data.
Instead, add a warning:
✅ "List the top five coffee-growing countries based on 2024 production data. Exclude any outdated information." >Including a verification step ensures that AI double-checks details, reducing errors.
4. Context Dump: Personalise the Response. Providing context helps AI generate a response that aligns with your specific needs and preferences.
Example Request Without Context:
❌ "What’s the best coffee for beginners?"
>This is too broad—"best" depends on personal taste, budget, and brewing method.
Instead, refine it with context:
✅ "I’m new to coffee and prefer a mild, low-acidity option. Recommend three coffee types that are beginner-friendly and easy to brew at home."
>With this added information, AI can suggest tailored recommendations rather than generic ones.
Putting It All Together: A Perfect AI Prompt Example
👉 Goal: I want a guide on beginner-friendly coffee types with a focus on taste and easy brewing methods.
👉 Return Format: Information provided in the form of a table with the following columns: Coffee Name, Flavor Profile, Best Brewing Method
👉 Warnings: Ensure the coffee recommendations are widely available in 2025 and exclude rare or expensive varieties.
👉 Context Dump: I’m new to coffee and prefer a mild, smooth taste with minimal bitterness. I have a basic coffee maker and a French press at home.
With this structured prompt, AI delivers a relevant, personalised, and well-organised response.
--adapted from Four Pillars of AI Prompting by OpenAI’s President Greg Brockman —Master AI Like a Pro!
Sources for this guide
Unless otherwise noted, the content of this guide is either adapted or taken from "A student guide to navigating college in the artificial intelligence era" by Elon University under the Creative Commons Attribution NonCommercial 4.0 International License 