Prompt engineering is the practice of creating and refining a description, question, and or instructions to enable an AI tool to construct the information most relevant to your topic and present it in a desired format. Consider the following parameters.
A table of AI output assessment criteria using the acronym PROMPT
| P | Persona | Specify whose voice or persona should shape the reply (poet, biologist, first-year student; expert in the field; journalist; lawyer; geographer; librarian) |
| R | Reduce Bias | Add detail to reduce AI output bias (e.g. gender, language, sources). For example, add the type of information that you would like to include or omit in your prompt; e.g., not social media; include grey literature sources. |
| O | Output | State the type of desired output (e.g. cover letter, code, thesis statement, dialogue, summary, poem, overview) |
| M | Model | Provide an example as appropriate to better explain what is required |
| P | Purpose | Describe specific needs, background, and context |
| T | Test | Test and refine to learn and improve how the tool is interpreting your prompt |
An example of applying PROMPT
In the voice of a professor teaching first-year university students and using only academic peer-reviewed sources from scholarly journals, summarize the pros and cons of arguments for teaching students how to use ChatGPT in their research. For example, discuss how it might impact their research skill development and motivation to learn. Present the information in a bulleted list and include specific references.
|
Persona |
In the voice of a professor teaching first-year university students |
|
Reduce bias |
Using only academic peer-reviewed sources from scholarly journals |
|
Output |
Present the information in a bulleted list and include specific references. |
|
Model |
For example, discuss how it might impact their research skill development and motivation to learn. |
|
Purpose |
Summarize the pros and cons of arguments for teaching students how to use ChatGPT in their research |
|
Test |
Lo, L. S. (2023). The art and science of prompt engineering: a new literacy in the information age. Internet Reference Services Quarterly, 27(4), 203-210.
Lo, L. S. (2023). The CLEAR path: A framework for enhancing information literacy through prompt engineering. The Journal of Academic Librarianship, 49(4), 102720.