Skip to Main Content

Artificial Intelligence

This guide is created for the UMGC community, with resources and information about Artificial Intelligence that can help students, faculty, and the greater community.

Prompting AI

Prompts, or messages, are the instructions we give to ChatGPT and other AI tools to help them create content we want. The more specific your prompt, the better content ChatGPT will create for you. Prompting ChatGPT each step of the way guides it to generate consistent, on-topic content. 

Whether you are asking a question or providing additional context, you are prompting ChatGPT to perform a task for you. A prompt consists of a few words, a single sentence, or paragraphs. Successful prompts influence the quality and relevance of ChatGPT's output and your satisfaction with the AI-generated content. Providing as much instruction and context as you can to ChatGPT will help it create content that matches your needs.

Here are some common tasks you can ask AI to perform:

  • text generation
  • image generation
  • questions & answer
  • problem solving
  • writing code
  • data analyzation
  • text summarizing & synthesizing 
  • writing posts, essays, & articles
  • language translation

CLEAR Framework

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

C: Consise: "brevity and clarity in prompts"

  • This means to be specific in your prompt. 

L: Logical: "structured and coherent prompts" 

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

E: Explicit: "clear output specifications"

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

A: Adaptive: "flexibility and customization in prompts"

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

R: Reflective: "continuous evaluation and improvement of prompts" 

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

For more info, read Lo's article: A framework for enhancing information literacy through prompt engineering.

Crafting Effective Prompts

Instruction: Include explicit instructions for the desired behavior, such as asking ChatGPT to think step by step, to rephrase an idea, to summarize an idea, or to synthesize two or more ideas. If you are able to, include context as well. 

  • User Example: I am preparing an undergraduate level 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.

Context: Providing context to ChatGPT will help it understand its task. Explaining your role, ChatGPT's role, the expected outcomes, or why you are asking for this completed task will help with a better outcome. 

  • User Example: I am an undergraduate student preparing a presentation on biofuels to my energy & engineering class. Please provide me with a step by step guide in getting started. 

Instruction and context work well when used together. Prompting ChatGPT to give you the best output takes trial and error, so reword your prompt a few ways to see what generates the best response. 

Clarifying Questions: Have ChatGPT ask questions to clarify what output you want. 

  • User Example: “Please ask me all the questions you need to understand my prompt”. 

Tone and Direction: Guide ChatGPT to generate content in a particular direction, style, tone, or format.

  • User Example: "Write a 250-word summary in an academic tone about the connection between biodiesel and crop waste." 
  • User Example: "Take the key points from the previous answer and write a response in a professional tone." 
  • User Example: "Synthesize this article and break the arguments down to a grade-12 level" 

Provide Examples: Provide an example that you have already created or have found, such as demonstrations of the output needed, a set of keywords, or a reference text.  

  • User Example: Find me 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. 

Act as Expert: Have the generative AI teach you about the topic you are interested in. 

  • User Example: “I am going to conduct a narrative review on Mitral Valve Repair vs. Replacement. I want you to act as an expert. I will ask you some questions and you will advise me on how to approach each step.” 
  • User Example: “Guide me through the concept of [topic] in [subject] through an example”. 

Other tips: 

  • Divide a large topic or question into smaller questions and ask ChatGPT step by step. 
  • Create "New Chats" for each unrelated question and topic so ChatGPT can start fresh. You can also ask ChatGPT to ignore the previous information you have given it.  
  • Copy and paste your research question into ChatGPT to receive feedback, ask for step-by-step instructions on the research process, or provide counterarguments to your premise. 

More Examples

Words to Include for Performing Specific Tasks: 

  • write/ explain/ summarize/ compose...
  • provide/ analyze/compare & contrast....
  • Rephrase/ Rewrite/ Reword...
  • Expand on the following...
  • Create....

To Ask Specific Questions: 

  • Who/ What/ When/ Where/ Why/ Whose/ Which....
  • How did...
  • How to...

To Include Specific Contexts: 

  • Write...in an academic tone in 500 words. 
  • Explain how to...in a professional setting.

Attributions