Skip to content
KPI

Learn

Writing Effective Prompts

Learn the foundational skills to write effective prompts when using AI assistants. Think of a prompt as a conversation starter with your AI-powered assistant.

The Four Main Areas

1

Persona

Define who the AI should be. Example: "You are a program manager in healthcare..."

2

Task

Describe what you want the AI to do. Example: "Draft an executive summary email..."

3

Context

Provide relevant background information. Example: "based on Q3 program docs and recent feedback..."

4

Format

Specify how you want the output structured. Example: "Limit to bullet points..."

Example Prompt Using All Four:

You are a program manager in healthcare. Draft an executive summary email to stakeholders based on Q3 program docs and recent feedback. Limit to bullet points.

You don't need to use all four in every prompt, but using a few will help! Always remember to include a verb or command as part of your task.

Quick Tips

1

Use natural language

Write as if you're speaking to another person. Express complete thoughts in full sentences.

2

Be specific and iterate

Tell the AI what you need it to do (summarize, write, change the tone, create). Provide as much context as possible.

3

Be concise and avoid complexity

State your request in brief — but specific — language. Avoid jargon.

4

Make it a conversation

Fine-tune your prompts if the results don't meet your expectations. Use follow-up prompts and an iterative process.

5

Use your documents

Personalize the AI's output with information from your own files. Reference specific documents when relevant.

6

Make the AI your prompt editor

Start your prompts with: "Make this a power prompt: [original prompt text here]." The AI will suggest improvements.

Advanced Techniques

1. Provide context

Before:

Tell me about climate change.

After:

Explain three major impacts of climate change on agriculture in tropical regions, with examples from the past decade.

2. Show examples

Before:

Please convert this technical statement to plain language.

After:

Here are two examples of how to convert technical jargon:

  • • "Quadratic speedup" → "Roughly twice as fast"
  • • "Intuitive design paradigms" → "Easy to use"

Now convert: "The platform implements end-to-end encryption."

3. Break complex tasks into steps

Before:

Analyze this quarterly sales data.

After:

Analyze this quarterly sales data by:

  • • Identifying top-performing products
  • • Comparing current to previous quarter
  • • Highlighting unusual patterns or trends
  • • Suggesting possible reasons for trends

4. Ask it to think first

"Before answering, please think through this problem carefully. Consider the different factors involved, potential constraints, and various approaches before recommending the best solution."

5. Define the AI's role

"Please explain how rainbows form from the perspective of an experienced science teacher speaking to a bright 10-year-old who's interested in science."

6. Assign a role for creativity

Start with: "You are the head of a creative department for a leading advertising agency..." to encourage creative outputs.

7. Give constraints

Include details like character count limits, number of options, or specific requirements: "Generate 5 options, each under 100 words."

8. Consider tone

Specify: formal, informal, technical, creative, casual, enthusiastic, professional, friendly, etc.

The Golden Rule

Show your prompt to a colleague, ideally someone who has minimal context on the task, and ask them to follow the instructions. If they're confused, the AI will likely be too.

Ask the AI for Help with Prompting

When you're not sure how to ask for something, try: "I'm trying to get you to help me with [goal]. I'm not sure how to phrase my request to get the best results. Can you help me craft an effective prompt for this?"

This is perhaps the most powerful technique of all!