Skip to Main Content

Generative artificial intelligence: Use at University

CLEAR prompt design

Adapted from Lo. L. S., 2023, 2024.

  • Brief with no unnecessary details
  • Clarity i.e., it needs to make sense
  • Natural progression of tasks
  • Context and relationship between ideas is clear
  • Precise instructions and specific
  • Audience e.g. public, academic, marketing team, etc.
  • Reading level e.g. primary school, first year undergraduate, experienced researcher, etc.
  • Tone e.g. humorous, professional, academic
  • Output format e.g. table, graph, image, essay, bullet list, etc.
  • Scope e.g. brief vs detailed
  • Sources e.g. journals
  • Discipline specific terminology
  • Give it examples to follow
  • Be flexible in your approach as it is an iterative process
  • Revise and experiment
  • Critically evaluate output using the CRAAP test
  • Fact-check using scholarly sources e.g. peer-reviewed journal articles via the library

Further reading

Bozkurt, A. (2024). Tell me your prompts and I will make them true: The alchemy of prompt engineering and generative AI. Open Praxis, 16(2), 111-118. https://doi.org/10.55982/openpraxis.16.2.661  

Lo, L. S. (2023). The art and science of prompt engineering: A new literacy in the information age. Internet reference services quarterly, 1-8. https://doi.org/10.1080/10875301.2023.2227621

Lo, L. S. (2023). The clear path: A framework for enhancing information literacy through prompt engineering. The Journal of Academic Librarianship, 49(4), Article 102720. https://doi.org/10.1016/j.acalib.2023.102720

 

Video (1 hour - start at 20 mins.)

Common mistakes

Adapted from Giray, 2023.

Prompt is too general lacking specific instruction or examples.
Reinforcing stereotypes, assumptions, sexism, etc.
Too specific limiting variety and diversity in output.
Not giving enough background so that GenAI can generate a more detailed and relevant response.
Promoting illegal and/or dangerous activities.
Take care when developing complex prompts as GenAI may get confused and generate an unexpected response.
When developing prompts be aware of the limitations of the GenAI that you are using.

Further reading

Giray, L. (2023). Prompt engineering with ChatGPT: A guide for academic writers. Annals of Biomedical Engineering, 51(12), 2629-2633. https://doi.org/10.1007/s10439-023-03272-4 

Heston, T., & Khun, C. (2023). Prompt engineering in medical education. International medical education, 2(3), 198-205. https://doi.org/10.3390/ime2030019 

Websites

Books