Generative AI (such as ChatGPT or Dall.e2) requires a prompt in the form of text. Other generative AI will have a series of prompts for users to select in order to generate content or will require a file to be uploaded to the generative AI tool.
Rarely do you get the right result on the first try. Learning to write prompts well in ways that AI systems understand is a learned skill. Learning how to write prompts effectively will ensure success. Most of the time, one prompt alone isn't enough to come up with the right answer, which requires you to iterate on your prompt with further inquiries.
You will always have better results the more specific you are, the more context you give it about the writing you want it to do. Often, the best results are achieved when, rather than tell the AI you want it to do something, you instead ask it to role play a situation.
Think about including:
The purpose of CLEAR is to provide a methodology for effective queries (prompts) when using generative AI tools. This framework is designed for academic research in mind, but also applies to outside this specialty.
A concise prompt removes superfluous information. Unclear or imprecise instructions can result in an output that does not match your prompt's intent.
Writing an effective prompt requires your question to be specific and directed.
Example:
| Use a more concise and explicit prompt such as “Explain the process of photosynthesis and its significance” instead of “Can you provide me with a detailed explanation of the process of photosynthesis and its significance?” | Instead of requesting, “Please provide me with an extensive discussion on the factors that contributed to the economic growth of China during the last few decades”, use a concise prompt like, “Identify factors behind China's recent economic growth.” |
Logical prompts adhere to basic fundamental knowledge. Ensure that information follows a natural progression and relationships are evident. This mainly pertains to sentence structure and context.
Example:
|
“List the steps to write a research paper, beginning with selecting a topic and ending with proofreading the final draft” is a logically structured question.
|
A logically structured prompt could be, “Describe the steps in the scientific method, starting with forming a hypothesis and ending with drawing conclusions.” |
Explicit prompts provide precise instructions in regards to format, content, or scope. Precise structuring includes types of information and how it should be supplied to you.
| Instead of, “Tell me about the French Revolution,” an explicit prompt would be, “Provide a concise overview of the French Revolution, emphasizing its causes, major events, and consequences.” | Rather than prompting, “What are some renewable energy sources?”, opt for a more explicit version like, “Identify five renewable energy sources and explain how each works.” |
Adaptive prompts require adapting your structure and prompt with different formulations, structures, and formats. You must adapt your responses to the generative AI's output and be flexible.
| If an initial prompt such as “Discuss the impact of social media on mental health” elicits responses that are too general, consider a more focused and adaptable prompt such as “Examine the relationship between social media usage and anxiety in adolescents.” | If asking, “What are some ways to conserve water?” leads to generic responses, try a more targeted and adaptive prompt like, “List household practices for conserving water and their potential impact.” |
When creating your prompt and evaluating the output, using a reflective perspective allows you to identify strengths, weaknesses, and areas to iterate in your information search. Generative AI can create work that is incorrect, incomplete, or non-representative. Adopting this framework, alongside lateral research methodology such as SIFT or CRAAP will allow you to fully understand AI output.
Adapted. 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
Examples of how to use the PROMPT Design Framework to optimize output from generative AI platforms.
Assign a role.
“You are a [literary critic / compliance officer / patent attorney / etc.]”
Define the parameters for output.
Topical content to include / exclude, number of responses, word count / limit, reading level, standards compliance, etc.
Describe the structure of output.
Alphabetical, chronological, table, bulleted or numbered list, step- by-step instructions, etc.
Describe the format of output.
Prose, social media post, computer code, spreadsheet, website, slide deck, image, A/V, recipe, dialogue script, survey, interview, etc.
Identify the rhetorical purpose and intended audience.
Explain, summarize, pitch, entertain, College students, English language learners, investor, first date, etc.
Specify the tone of output.
Academic, professional, snarky, funny, inspirational, sentimental, foreboding, etc.
Digital Shred Privacy Literacy Toolkit by Alexandria Chisholm & Sarah Hartman-Caverly, 2025, is licensed under CC BY-NC-SA 4.0 International.