The CLEAR Framework for Generative AI Prompt Engineering was developed by Leo S. Lo.
| CLEAR Framework's 5 Frames | User Prompt Examples |
| Concise: Brevity and clarity | Explain the process and significance of osmosis. |
| Logical: Structured and coherent | List the steps of the Nursing Process. |
| Explicit: Clear outcome specifications | I am writing an undergraduate level research paper for an English class on the impact of social media on teenagers' mental health. Write a list of 3 key arguments for and against teenage social media usage. |
| Adaptive: Flexibility and customization | If a prompt like "Tell me more about sleep deprivation" produces generic answers, we can update and customize our prompt to address our information need, such as "What are some strategies to maintain a consistent sleep schedule with toddler children and a full time job?" |
| Reflective: Evaluate and improve your prompts based on your evaluation of the gen AI responses | After we read an AI-generated list of the pros and cons of daily caffeine consumption, consider using an information evaluation framework such as CCOW to evaluate the results based on accuracy, relevancy, and comprehensiveness. We might use our reflection on this evaluation to adapt future prompts. |
Parts of this table are adapted (with changes) or reused from a guide created by Bronte Chiang at the University of Calgary. The University of Calgary guide is under a Creative Commons Attribution 4.0 International License.
"Being “AI literate” is the ability to understand, use, and reflect critically on AI applications without necessarily being able to create and develop AI models like someone with a computer science background. Understanding how to use AI as a tool to enhance your work is how you become AI literate." -- University of Calgary Libraries