A prompt is the instruction you give to Copilot. The clearer your direction, the better the response. This module shows you how to structure prompts that get useful results on the first try.
Structure prompts
Use frameworks to organise your requests
Apply patterns
Copy proven formats for common tasks
Enrich inputs
Add files, references, and context to your prompts
A prompt is the way you tell an AI what you want and how you want the result to look. A good prompt doesn’t just say what to do. It often includes context, tone, format, or constraints to guide the result.Think of it as having a conversation with a very knowledgeable assistant who needs clear directions to help you best.The more precise you frame your request and prompt, the more accurate your responses can be.
Text is not your only input. Copilot can work with your Microsoft 365 data, files, and references to give you faster, more accurate results.
Work vs Web toggle
Switch between two data sources depending on your task.Work modesearches your Microsoft 365 data including emails, Teams chats, documents, and calendar events. Use this for internal tasks.Web modesearches the public internet for current information and general knowledge. Use this for external research.Try this:Toggle to Work mode and ask Copilot to summarise your recent emails from a specific colleague.
Reference with slash commands
Use the ’/’ command to reference specific files, people, or meetings.Type ’/’ followed by a file name, person’s name, or meeting to attach context directly to your prompt.Copilot can then search relevant emails, documents, and Teams messages.Try this:Type ’/[colleague name]’ to prepare for a meeting by pulling recent communications with them.
Combine Work mode with slash commands for the most relevant results. Reference a specific document with ”/” and Copilot will use it as context for your request.
Once you are comfortable with the basics, these techniques help you tackle more complex tasks.
Chain prompting
Break complex tasks into smaller steps. Complete one step before moving to the next.
1
First prompt
“Help me brainstorm topics for a presentation about climate change”
2
Second prompt
“Now help me create an outline for a presentation about renewable energy solutions”
3
Third prompt
“Create detailed content for the first three slides of this outline”
Iterative refinement
Start broad, then narrow down based on the response you receive.
1
Initial
“Help me plan a team building event”
2
Refine
“Focus on indoor activities for 15 people with a budget of $500”
3
Finalise
“Create a detailed timeline for a cooking class team building event”
Constraint setting
Add specific limitations to get focused results.
Write a product description for wireless headphones with these constraints: - Maximum 100 words - Highlight 3 key features - Use conversational tone - Include a call-to-action - Target audience: fitness enthusiasts
Multi-perspective prompting
Ask Copilot to analyse from different viewpoints.
Analyse the decision to work remotely from three perspectives: 1. Employee benefits and challenges 2. Employer costs and benefits 3. Impact on team collaboration Provide balanced insights for each perspective.
Scenario planning
Explore different possibilities before committing to a plan.
Help me plan for three scenarios for our product launch: 1. Best case: High demand, no technical issues 2. Worst case: Low demand, technical problems 3. Most likely: Moderate demand, minor issues Provide action plans for each scenario.
Good prompting is like briefing a capable colleague. The clearer you are about what you need, the better Copilot can help. Start with the frameworks, practise with different patterns, and refine your approach based on what works for your tasks.You are done with this module when you can do the following:
Structure prompts
You can apply at least one framework to a real task
Apply patterns
You have used a prompting pattern from this module
Enrich inputs
You have tried Work mode or slash commands
Refine outputs
You have used follow-up prompts to improve a response
Ready to practice?
Complete the challenge by building a prompt using what you have learned