The Prompt Engineering Guide by DAIR.AI has many more techniques and guidelines for prompt engineering:
A prompt is (technically speaking) input to an AI tool. For research AI tools, the prompt is almost always a question, request, or topic posed by you, the human researcher. Why should you try to write good prompts?
Good prompts are CLEAR – a framework developed by Leo Lo, a librarian and professor at the University of New Mexico.
| Good | Needs Improvement | |
| Concise (also Clear) - Focus on the key words for the AI tool to analyze. Try to omit as many needless words* as possible. | Identify the top reasons to pursue a college degree. |
I am trying to figure out if I should be applying to college and if I would like it there. (The AI doesn't know you or your preferences, there are multiple institutions, etc.) |
|
Logical - Most AI tools look for relationships between words and concepts, so make sure your query presents concepts accurately and in their natural or logical order. If your question doesn’t make sense to you (or to someone else), it probably won’t make sense to the AI! |
Summarize the most promising vaccine candidates that protect against multiple strains of influenza. |
Can we make a flu vaccine organically? (Are you asking about a vaccine made with eggs obtained through organic farming? A vaccine developed through "organic" research? Something else?) |
| Explicit - Be clear in what you want from the AI. Giving the AI tool clear output directions can help the AI produce an answer that is useful to you. | Give me a concise summary of the major strengths and weaknesses of the University of Indianapolis. |
What’s The University of Indianapolis like? (What's your comparison for UIndy? Do you want a short answer or a long one?) |
Even the best prompts may need improvement! The last two components address what to do after you’ve examined the AI’s answer to your initial prompt.
| Adaptive - Try a second prompt with keywords or topics suggested by the AI in its answer. If the AI tool has seeding or guidance settings, investigate different settings - do you get better results? If the tool allows you to specify words/concepts to exclude or ignore, can you refine your prompt by excluding concepts? |
Prompt 1: Why doesn’t UIndy have a parking garage? Answer: (includes "geographical obstacles") Prompt 2: What are the engineering challenges and geographical obstacles to constructing a parking garage at UIndy? |
|
Reflective - Always take a moment to reflect on the AI’s answer. Does it make intuitive sense to you? Does the answer refer to current research (if important for your query), or does it seem based on older research? Has the AI “hallucinated” or returned inaccurate information? Is the answer complete, or are there perspectives or voices unrepresented in the answer? You may need to craft additional prompts that specifically target gaps in the initial answer. |
Prompt 1: Give me a concise summary of the major strengths and weaknesses of The University of Indianapolis. Prompt 2: Give me a concise summary of the major strengths and weaknesses of The University of Indianapolis, from the perspective of a first-generation college student. |
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
*Strunk, W. & White, E.B. (2005). The Elements of Style. Penguin. (Original work published 1979)
Articles on Prompt Engineering.