UWM Libraries Research and Course Guides: Political Science 398: Cyberpolitics: Write effective prompts

What is generative AI?

Generative artificial intelligence (GenAI) is a type of artificial intelligence that creates new content. GenAI is possible with large language models (LLM) that are trained on massive amounts of text content or data. Each LLM is trained on a particular set of data, which might come from website, social media, and internet forum crawls, news sites, copyrighted or public domain materials, scientific articles, etc, for its intended purpose. GenAI generates outputs based on prompts. Responses are a prediction of subsequent units of meaning (tokens) to generate text that resembles natural language based on that particular LLM's training materials. However, GenAI creates content independent of context. This means that it can sometimes "hallucinate", or generate content that is inaccurate or that doesn't make sense, including book and article citations, data, recent events.

Notable generative AI LLMs and their applications

GPT-4o (OpenAI ChatGPT, Bing Co-Pilot)
LLAMA-3.1 (Meta)
Gemini 2.0 (Google, formerly Bard)
Claude-3.5 (Anthropic)
DeepSeek-V3

Notable text-to image generative AI applications

Midjourney
DALL-E (OpenAI)
Stable Diffusion (Stability AI)
Gemini (Google)
Firefly (Adobe)

Writing prompts

Prompts are the instructions you input into the AI system to generate content. The AI system is responsive and you can use additional prompts to refine the AI system's outputs. There are a few frameworks for crafting effective prompts. Effective prompt writing takes practice.

Getting started with prompts for text-based Generative AI tools
The information, sentences, or questions that you enter into a Generative AI tool (“prompts”) are a big influence on the quality of outputs you receive. More descriptive prompts can improve the quality of the outputs. This guide gives you a basic overview of how to Generate better prompts.
Getting started with prompts for image-based Generative AI tools - Harvard
This guide gives you a basic overview of how to generate prompts for image-based AI tools.
How to write effective AI art prompts - Zapier
Good prompts are the backbone of good outputs. This is true for ChatGPT and even more so for AI image generation tools. But while ChatGPT provides solid responses even with super basic prompts, AI art generators tend to require more attention to detail—and more attempts—before you get what you're looking for.
AI Learning Resources
ere, you can explore a comprehensive collection of resources, featuring everything from ChatGPT and Midjourney to Stable Diffusion, Google Bard, and other AI tools. Dive into cheat sheets, AI courses, prompt engineering tutorials, and more to enhance your understanding and skills in AI.

Frameworks for writing prompts for generative AI

CLEAR Framework (Lo, 2023)
- Concise: brevity and clarity in prompts
- Logical: structured and coherent prompts
- Explicit: clear output specifications
- Adaptive: flexibility and customization in prompts
- Reflective: continuous evaluation and improvement of prompts
CRISPE Framework (Nigh, 2023)
- Capacity and Role: What role (or roles) should the app act as?
- Insight: Provides the behind the scenes insight, background, and context to your request
- Statement: What you are asking the app to do
- Personality: The style, personality, or manner you want it to respond in
- Experiment: Asking the app to provide multiple examples for you