A prompt is the input provided to an AI tool. In research-focused AI tools, it is typically a question, request, or topic defined by the human researcher. Writing good prompts is essential for several reasons:
Good prompts enhance AI performance: A well-structured prompt enables the AI to deliver accurate, meaningful, and relevant results. On the other hand, poorly written prompts can lead to irrelevant or unhelpful outputs, hindering your research process.
Good prompts save money: Many AI research tools operate on a pay-per-task or credit-based system. Crafting effective prompts helps you achieve the desired results in fewer attempts, reducing overall costs.
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 impact of university education on career outcomes. |
I am trying to figure out if a degree will help me get a good job? (The AI doesn't know you or your preferences, there are multiple "Georgetown" institutions, & are you applying to high school? Undergrad? Grad school?) |
|
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 key factors to consider when choosing a neighborhood to live in. |
What’s it like living in the city? (What's your comparison for living in a city? 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: How do different university majors influence job market demand? Prompt 2: What role does university education play in determining career advancement opportunities? |
|
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: How do you balance affordability with quality of life in a neighborhood? Prompt 2: How important is proximity to public transportation when selecting a neighborhood? |
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)
This guide provides strategies and tactics for improving results from large language models, often called GPT models, such as GPT-4o by OpenAI.
A comprehensive guide to prompt design for various generative AI tools and prompt engineering.
The ChatGPT Prompt Engineering for Developers course offers valuable insights into utilizing large language models (LLMs) to create innovative and powerful applications efficiently.
Discover how to use Copilot Prompts and learn effective strategies for crafting prompts.
Develop prompts to create lesson plans and complete administrative tasks