Effective Prompt Writing for AI

Written by Marion Millard-Grelet

The quality of outputs you receive from a Generative AI tool relies heavily on the information, sentences, or questions you input, referred to as "prompts". Once you enter a prompt, the AI model analyses your input and generates a response based on the patterns it has learned during its training. The quality of your prompts directly impacts the quality of the AI’s response.

This article gives you a basic overview of how to generate better prompts, so you receive valuable responses.

An effective prompt should contain the following elements:

• Goal – A high-level overview of what you are trying to achieve. This can be instructions or a question, but it should indicate what you want out of your current session.
• Context – The relevant background information, details or circumstances needed to clarify the purpose, scope or requirements of your request.
• Expectations – The format or audience you want your response tailored to.

Useful Tips

1. Be Specific: A generic prompt like “create a Microsoft list view” will produce a generic response. Who will be using the view? What sort of data are you working with? How is the data structured? Are there any required columns?  Adding this type of context and being specific, clear and concise will help generate more useful outputs.
2. Give Examples: Providing the AI with an example of how you’d like the output can provide contextual understanding and improve results.
3. Have a conversation: Chat with the AI as if it’s a colleague or teammate you’re working on a project with. Start with an initial prompt and build on it to progressively add clarity and context. Give feedback – if you notice it got it wrong, tell it so it can correct its mistake.
4. Be polite: You never know now when AI might take over, stay in their good books!