Ivy Tech Libraries: Generative AI: Prompt Design

Learn AI Prompting

Prompt Engineering Guide
A comprehensive (and free) guide on how to use GenAI. This course is tailored to non-technical readers, who may not have even heard of AI.
Linkedin Learning Courses
For AI prompt engineering. Please note: students must be logged in to MyIvy to gain full, free access to LinkedIn Learning tutorials.
Ivy Tech Skills Training Classes
Purdue Library Prompt Design Guide
Prompt Engineering for ChatGPT
Vanderbilt University Coursera Course

O'Reilly for Higher Education
Thousands of ebooks, audio books, videos, covering computer networking, software development, programming, and more.

What you specifically ask a generative AI will influence its output. Here are a few methods to help you improve your prompts.

Prompt Framework

Prompt framework for students: the five "s" model. (n.d.). AI for Education. https://www.aiforeducation.io/ai-resources/the-five-s-model-students

Prompt Structure

The information, sentences, or questions that you enter into a Generative AI tool (“prompts”) influence the quality of outputs you receive. When writing prompts, it is important to:

Give it some context or a role to play. For example "I am a college student..." or "Act as if..."
Be specific. Give detailed instructions and examples.
Tell it how you would like the results formatted: a list, a table, paragraphs, even emojis.
Tell AI what you do and don't want in the output.

Examples

I'm a college student working on a research paper about music therapy. I want help finding keywords on the topic to search in academic databases. Generate a list of 5 keywords I can use to search for this topic.

I am an undergraduate student writing an English paper. The research theme is "Why Read?" I need help figuring out where to start my research. Ask me questions to help me start my research.

I am a college student writing a research paper on the American Civil War. I need suggestions on steps to take to narrow down my topic. Ask me questions to help me narrow my research topic.

from Using GenAI Effectively, Arizona State University and Getting started with prompts for text-based Generative AI tools, Harvard University

The CLEAR Framework for Prompt Engineering

Quality prompts have five components

Concise: brevity and clarity

Logical: structured and coherent

Explicit: clear output specifications

Adaptive: flexibility and customization

Reflective: continuous evaluation and improvement

Examples of each component

Concise:

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?”

Logical:

A logically structured prompt could be, “Describe the steps in the scientific method, starting with forming a hypothesis and ending with drawing conclusions.”

Explicit:

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:

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.”

Reflective:

After receiving AI-generated content, evaluate the response's accuracy, relevance, and completeness.

from 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