Prompt engineering is the practice of designing inputs for generative AI tools that will produce optimal outputs.
Dr. Leo Lo, Dean of the College of University Libraries & Learning Sciences at the University of New Mexico, has developed a framework for effective AI prompt engineering. The CLEAR framework is comprised of five characteristics.
| Concise | Logical | Explicit | Adaptive | Reflective |
| Brevity and clarity in prompts | Structured and coherent prompts | Clear output specifications | Flexible and customizable prompts | Continuous evaluation and improvement of prompts |
|
Replace: “Can you provide me with a detailed explanation of the process of photosynthesis and its significance?” |
Illogical: "Compare the scientific method with the non-scientific method." | Replace: “What are some renewable energy sources?” | Replace: “Describe the history of computers” | After acquiring an AI-generated list of strategies for effective time management, evaluate the relevance and applicability of each strategy. |
| With: “Explain the process of photosynthesis and its significance” | Better: "Describe the steps in the scientific method, starting with forming a hypothesis and ending with drawing conclusions." | With: “Identify five renewable energy sources and explain how each works.” | With: “Explain the development of personal computers from the 1970s to the 1990s.” | Consider the target audience's needs, and use this information to tailor future prompts to generate content that better addresses specific challenges or contexts. |