According to Stanford, prompt engineering is "the process of designing and refining input prompts to effectively guide the behavior of AI models, particularly large language models (LLMs) like GPT-4, to produce desired outputs. As these models do not have a fixed set of commands or instructions, the way questions or requests are phrased can significantly impact the quality and relevance of the AI's response."
Essentially, prompting AI means telling AI what to do in a way that makes it more precise and likely to do what a person wants.
An example that Dr. Robbie Melton, the Vice President for Technology Innovations at TSU, shared with faculty previously is the prompt: "acting as [an academic researcher on this topic], find information on [topic]". If a student would like to find information about certain subjects, that student should tell the AI to search while acting as an academic researcher on the topic. Another excellent prompt is "find information on [this topic] and explain it like I'm five."
There are many ways to prompt AI.
15 Tips to Become a Better Prompt Engineer for Generative AI - from Microsoft
AI Demystified: What is Prompt Engineering? - from Stanford
Prompt Design Strategies - from Google
Getting started with prompts for text-based Generative AI tools - from Harvard
Prompt Engineering - from OpenAI
Prompt Patterns - from Vanderbilt
Prompt Vine - AI prompt library