Research Guides: Artificial Intelligence: Tools for Faculty: AI Tools & Prompts

Popular Generative AI Tools

ChatGPT
ChatGPT, developed by OpenAI, is a generative AI tool that specializes in creating human-like text for conversational AI. Its capabilities extend to answering questions, simulating detailed conversations, writing diverse forms of content, and even coding.
Gemini (formerly known as Bard)
Created by Google, Gemini represents a significant stride in the generative AI landscape, leveraging large language models. It is designed to deliver detailed and accurate information, potentially integrating with Google's vast search database to provide real-time, up-to-date information
Midjourney
Midjourney stands as a generative AI tool focused on image generation, distinguished by its specialized algorithms and output quality. It is designed to create compelling visual content based on various inputs, finding its use in art, design, and content creation.
Microsoft Copilot
Chatbot powered by Microsoft's proprietary Prometheus, which combines GPT-4 (which also powers the subscription version of ChatGPT) and Bing web search. Copilot's Designer is powered by DALL-E 3. Copilot can help users with a variety of tasks, such as writing code, generating text, creating graphic art from text descriptions, and finding information on the web. As of early 2024, Copilot is considered the best free alternative to a paid ChatGPT subscription.
Perplexity
Perplexity AI is an AI-powered search engine and chatbot that is designed to provide accurate and comprehensive answers to user queries. By searching the web in real-time, it offers up-to-date information on a wide range of topics. It is particularly notable as the only chatbot with an "Academic" Focus setting.

Prompt Tips

From the Wharton School, University of Pennsylvania

How to use google's notebook

Help for Writing Prompts

AI Prompts 101: Understanding How They're Created & Used
Includes guidelines for writing AI effective AI prompts.
AI Prompts for Teaching: A Spellbook
From Cynthia Alby, Ph.D. - examples of AI prompts for tasks within and outside of the classroom.
Best Practices for Prompt Engineering with OpenAI API
Covers how to give clear and effective instructions to OpenAI models. Includes rules of thumb and examples of how to fine-tune prompts.
A Guide to Prompting AI (for what is is worth)
Tips for writing AI prompts From Ethan Mollick, Wharton School, University of Pennsylvania.
Prompt Engineering Guide: Examples of Prompts
Examples of tasks include: text summarization, information extraction, question answering, text classification, conversation, code generation, and reasoning.

The CLEAR Framework

Good prompts are CLEAR – a framework developed by Leo Lo, a librarian and professor at the University of New Mexico.

The CLEAR Framework's Five Components:

C - Concise: brevity and clarity in prompts.
Remove superfluous words so AI can focus on the most important aspects of the task.
Example: "Explain the water cycle process and its significance."
L - Logical: structured and coherent prompts
To create a logical prompt ensure that the information provided follows a natural progression and the the relationships between concepts are relevant.
Example: "Describe the steps in the scientific method, starting with forming a hypothesis and ending drawing conclusions."
E - Explicit: clear output specifications
Explicit prompts provide precise instructions regarding the desired output format, content, scope.
Example: "Provide a concise overview of World War II, emphasizing its causes, major events, and consequences."
A - Adaptive: flexibility and customization in prompts
When crafting adaptive prompts, be flexible and willing to attempt new approaches based on the performance of the AI model.
Initial Prompt Example: "Discuss the impact of social media on mental health"
More Focused and Adaptable Prompt Example: "Examine the relationship between social media usage and anxiety in adolescents."
R - Reflective: continuous evaluation and improvement of prompts
Emphasizes the significance of continuous evaluation of AI-generated content and apply the insights obtained to future prompts.
Example: After receiving AI-generated content on the benefits of a plant-based diet, evaluate the response's accuracy, relevance, and completeness. Use the insights gained from the evaluation to refine future prompts, such as asking for more specific benefits or focusing on certain aspects of a plant-based diet.

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

Other Approaches to Writing Prompts

Tips for Rewriting Prompts:

rewrite as a specific author:
Rewrite this sentence in the style of ....
rewrite for a specific goal:
Rewrite this paragraph to make it more persuasive
rewrite for a specific tone:
Rewrite this sentence/paragraph to sound more...
Examples of tones: serious; lighthearted; formal; action-oriented, optimistic, etc.
rewrite for a specific demographic:
Rewrite this sentence/paragraph to appeal to a younger audience/professional audience/international audience