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
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.