Skip to Main Content

Artificial Intelligence (AI) Help Guide

An introduction to artificial intelligence (AI) with a focus on generative AI concepts and tools. Last updated: December 19, 2024

What is a prompt?

A prompt is the input that you enter into an AI tool to generate results. A prompt may be a question, instructions, or a set of search keywords.

Designing effective prompts—also called prompt engineering—helps enable AI tools to give you meaningful, accurate, and relevant results. Understanding the nuances of prompt creation and practicing good prompt design techniques are important components of AI literacy.

CLEAR: A Framework for Effective Prompts

Dr. Leo Lo, Dean of the College of University Libraries and Learning Sciences at the University of New Mexico, developed the CLEAR framework to describe five core principles of effective prompts for AI models like ChatGPT and Microsoft CoPilot.

Good prompts are CLEAR:

Principle Objectives Needs Improvement Revised Prompt
Concise
  • Focus on keywords
  • Eliminate unnecessary words
  • Be direct and specific in your requests
 "Please provide me with an extensive discussion on the various factors that have significantly contributed to the unprecedented rise of online learning in the United States in the past few years." "Identify factors behind the recent rise of online learning in the US."
Logical
  • Organize prompts into steps
  • Break complex tasks into smaller, focused prompts
 "Please outline a 5-minute speech on renewable energy resources and also include some data on air pollution in Washington, DC." "First, outline a 5-minute speech on renewable energy resources. Then, cite at least two statistics on air pollution in Washington, DC to support your argument."
Explicit
  • Provide clear, detailed instructions
  • Don't assume the AI knows what you want
  • Include specific details and output requirements
 "Tell me about the Haitian Revolution." "Give a concise overview of the Haitian Revolution, including its causes, major events, and consequences."

The final two principles of the CLEAR framework ask you to revisit your prompt after you've received a response from the AI tool.

Principle Objectives
Adaptive
  • Be flexible: rephrase or restructure your prompt if you didn't receive the response you expected
  • Revise your prompt to address inaccuracies or missing information
  • Adjust settings and parameters
Reflective
  • Evaluate the AI's response:
    • Does it make logical sense?
    • Does the response direct you to current research and include real citations?
    • Is the answer complete, or are certain voices and perspectives missing?
  • Consider what worked well and what didn't
  • Continuously improve your prompts

Learn more about the CLEAR framework:

Lo, L. S. (2023). The CLEAR framework for ChatGPT: Enhancing information literacy in the AI era. The Journal of Academic Librarianship, 49(5), 102720. https://doi.org/10.1016/j.acalib.2023.102720

Lo, L. S. (2023). CLEARer Dialogues with AI: Unpacking Prompt Engineering for Librarians [Video]. YouTube. https://www.youtube.com/watch?v=3pvmMEnJhCs‌​

More Tips for Effective Prompts

The CLEAR framework is just one model for designing effective prompts for generative AI tools. Other models include the PROMPT Design Framework (from Sarah Hartman-Caverly at Penn State University Libraries) and the CREATE Framework (from Dave Birss, a Generative AI Educator for LinkedIn Learning).

More tips for creating effective prompts for generative AI tools:

  • Try—and try again! Like doing research, prompting AI is an iterative process. Even well designed prompts may need refinement as you learn the limitations of each AI tool. 
  • Assign a role to the AI. Giving an AI tool a role to play provides it with context, sets expectations, and guides its behavior toward more relevant and tailored responses. For example, if you're looking for help brainstorming keywords for your research topic, you might prompt the AI tool to "act as an academic librarian." Or if you want to practice for a job interview, you may prompt it to "act as a hiring manager."
  • Give examples. Share example responses or templates with an AI tool to guide how it generates content.
  • Specify what not to include. In addition to prompting an AI tool for what you want it to include in its response, you can also prompt it to avoid specific content, language, or approaches.
  • Adjust the AI's temperature. In the context of AI, temperature is a parameter that controls the randomness of an AI model's output. For many free generative AI tools, the temperature is preset by developers to ensure a balance between creativity and predictability in responses. However, some AI tools allow you to change their temperature. Look for options that allow you to generate "more precise," "more creative," or "more balanced" responses.
  • Ask the AI to explain its processes. Not sure how an AI tool arrived at a response? Ask it for more information about how it got there, including its step-by-step reasoning, the factors it considered, and the sources it consulted. 

ask@udc.libanswers.com

202-274-5104

Facebook Twitter Instagram YouTube