AI has a wide range of uses that can be beneficial for research. Generative AI can be used to
Some grammar software uses AI to provide feedback and help with things like style or tone. Other types of AI that generate images, audio, video, or presentations have a wide range of uses.
Before using AI for any work at Lipscomb, make sure to check with your professor as to their AI policy for the class and assignments.
AI is only as useful as the questions or prompts provided by the user. To get good answers you must ask good questions. The process of creating good questions or commands is called prompt engineering. The CLEAR framework can help you formulate prompts that will give you the results you need.
| Good Prompt | Needs editing | |
|---|---|---|
|
C Concise (or Clear): Focus on the keywords and try to omit as many unnecessary words as possible. |
Identify the top reasons bubble tea has become popular in the United States in the past decade. |
I am trying to figure out why bubble tea has become popular all of a sudden. (The AI doesn't know what time period is meant by "all of a sudden" or where it has become popular. It could give you results about it becoming popular in Canada or someplace else.) |
|
L Logical: AI looks for relationships between words and concepts so make sure your prompt is logical and accurate. (If it doesn't make sense to you or someone else, it probably won't make sense to AI). |
Summarize the economic and cultural factors that led bubble tea to being imported and adopted in the United States. |
How did bubble tea come to the United States? (Are you asking about how the materials to make bubble tea are shipped to the US? The history of bubble tea?) |
|
E Explicit: Be clear on what you want AI to do or produce for you. Provide output directions to get the desired result. |
Give me a summary of the pros and cons of bubble tea from a nutrition perspective. |
Is bubble tea good? ("Good" as in taste or nutrition? In comparison to other foods? Do you want a long or short answer?) |
| The next 2 steps are more about altering and thinking about your prompts instead of creating better prompts. | ||
|
A Adaptive: You will need to refine your prompts based on the results the AI gives. This can involve telling the AI to elaborate more on it's previous answer or telling it to focus or ignore part of the previous response. Some AI have settings for this that are called guidance or seeding settings so play around with those to see if it helps you get better results. |
Prompt 1: Why is bubble tea made with tapioca? Answer: Includes steps in the bubble tea manufacture process. Prompt 2: Can bubble tea be made with other ingredients besides tapioca? |
|
|
R Reflective: Take a moment to reflect on what the AI has given you. Does it make sense? Is it based on new or old research? Has it hallucinated any data or given inaccurate information? What/Where is the AI getting this information? Is it reliable and credible? Are there biases in the AI response or are there some voices or perspectives not reflected? You may need to create more prompts to solve these issues or look into other resources besides AI. |
Prompt 1: Give me a brief overview of the cultural impact of bubble tea on the United States. Prompt 2: Give me a brief overview of the cultural impact of bubble tea on the United States among millennials and Gen Z. |
|
The CLEAR framework comes from 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.