Skip to Main Content

Old Gen AI guide (don't use))

NOTE: This guide is a work in progress and will continue to be updated as new generative AI resources, policies, and technologies are available.

Best Practices for Prompts

A prompt, for research AI tools, is usually a question, request, or topic posed by the researcher. In order to get the most precise, meaningful, and relevant results from AI tools, it's important for researchers to write good prompts. 

A useful tool for crafting prompts is the CLEAR Framework — Concise, Logical, Explicit, Adaptive, and Reflective (Leo, 2023). 

Concise (and Clear): Prompts should be brief and clear. Focus on keywords and avoid unnecessary words and jargon. 

Identify the optimal number of students in an online undergraduate course

Find research articles on gluten intolerance in humans

Logical: Prompts should be structured and coherent. The relationship between words, concepts, and the context should be clear.

Discuss the order and purpose of each section of a research article

Describe the sequence of steps in diagnosing carpal tunnel syndrome

Explicit: Prompts should set clear output specifications to produce an answer that is useful.

Identify five factors that led to the onset of World War I.

Describe the economic implications of climate change in developing countries over the next decade

Adaptive: Prompts should be flexible and customizable. Be willing to ask again in a different way, refining your prompt based on AI response.

1~What factors help nursing students pass the NCLEX on the first try

2~What student factors affect first-time pass rates on the registered nurse licensure exam

Reflective: AI output should be continually evaluated. You may need to craft additional prompts that target gaps or missing information in the initial response. 

  • Does the response answer your question?
  • Does it appear to be based on current research? 
  • Can the response research or source data be verified? 
  • Are there important perspectives not represented in the response?

 

Leo, L. S. (2023). The CLEAR path: A framework for enhancing information literacy through prompt engineering. The Journal of Academic Librarianship49(4), 102720. https://doi.org/10.1016/j.acalib.2023.102720

©2024 St. Catherine University Library, St. Paul, Minnesota, USA

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License