4.2 Prompt Engineering
Prompt Engineering
Many AI interfaces allow users to communicate using natural language, rather than programming or machine language. This makes it easier for general audiences to use Generative AI technologies; however, as with human-to-human communication, it’s important to use clear and specific language to get the desired results. The process of designing effective prompts is sometimes referred to as prompt engineering.
Effective prompt writing can help you more quickly achieve the results that you’re seeking, minimizing the number of queries that you need to make.
The following tips can help you write effective prompts to get the results you’re looking for:
For more tips, check out the Prompt Engineering Guide 
or the Prompt Library from Ethan Mollick .
Activity: Prompting AI
Using the Generative AI tool of your choice, try out some of the techniques shared above to accomplish the tasks below:
- Generate 20 practice questions for knowledge checking quizzes in the correct format for your course.
- Create an announcement text reminding students of an upcoming assessment deadline in a tone appropriate for your classroom culture.
- Design a creative learning activity that allows learners to apply key concepts from one of your courses to a task or puzzle.
- Generate a plan for an introductory lecture on a topic in your discipline that you’re not an expert in.
A subset of Deep Learning that can use learned rules or patterns to generate new content.
A prompt is the text that is provided to the system providing instructions on the desired output or the task being requested.
Examples of prompts:
For text-to-text:
Write a detailed case study demonstrating environmental racism in a Canadian context for a class of first year university students at a Canadian university.
Summarize the key themes of Orwell’s 1984 in a bulleted list and simple English.
For text-to-image
Generate a photorealistic depiction of Six Grandfathers Mountain before it was carved into Mount Rushmore.
