What is Prompt Engineering?
A prompt is the input you provide to an AI tool to produce results, such as a question, set of instructions, or a series of search keywords. Crafting effective prompts, also known as prompt engineering, is a key skill for using GenAI tools effectively. By understanding how GenAI operates and providing clear instructions and context, you can ensure the AI delivers meaningful, accurate, and relevant outcomes. There are many prompt models that can help with creating and structuring effective prompts. Some are highlighted below
TOCD Prompt Template - from KPU Teaching and Learning, based on Yi Zhou (2023).
- Task – The specific action you want the AI to perform, along with any relevant details.
- Output – Clear instructions on how the task should be carried out.
- Context – Information about the target audience or how the results will be used, helping the AI customize its response.
- Data – Details on the data to be included or excluded from the task.
PROMPT Design Framework by Sarah Hartman-Caverly, Librarian Penn State Berks
- Persona - assign a role
- Requirements - define parameters for output
- Organization - describe the structure of the output
- Medium - describe the format of the output
- Purpose - identify the rhetorical purpse and intended audience
- Tone - specify the tone of output (ex: academic)
Example using this framework:
- Original: Outline a paper about self-driving cars in cities with a lot of traffic
- New: You are a college student majoring in transportation engineering. Produce a numbered, multi-level outline for a 7 page academic paper for a college-level transportation engineering class about the challenges and solutions for introducing self-driving cars into a high traffic city.
The CLEAR framework, created by Librarian Leo S. Lo at the University of New Mexico, is a framework to optimize prompts given to generative AI tools. To follow the CLEAR framework, prompts must be:
- Concise: "brevity and clarity in prompts": This means to remain specific in your prompt.
- Logical: "structured and coherent prompts": Maintain a logical flow and order of ideas within your prompt.
- Explicit: "clear output specifications": Provide the AI tool with precise instructions on your desired output format, content, or scope to receive a stronger answer.
- Adaptive: "flexibility and customization in prompts": Experiment with various prompt formulations and phrasing to attempt different ways of framing an issue to see new answers from the generative AI
- Reflective: "continuous evaluation and improvement of prompts":
*This information is based on the following article: 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://go.exlibris.link/4s7l2zZV
Additional resources:
Prompt Engineering for Academic Research by New York Institute for Technology
Prompt Engineering for GenAI: Prompt frame works by Breda University
