Loading
PLATFORM
CAPABILITIES
ASANA AI
PLANS
Company Type
Teams
Industries
Use Cases
LEARN
SUPPORT
SERVICES
Help Center
search-icon

Topics

How to structure a prompt in AI Studio

In This Article

AI Studio is available for Starter, Advanced, Enterprise, and Enterprise+ customers. Visit asana.com/ai to learn more about the launch of Asana AI Studio.

This is a quick-start guide intended to get AI Studio creators producing effective prompts within a few minutes. For more detailed insights, we recommend reading the article Writing instructions in AI Studio. If you’d like to go further, you can also earn the AI Studio Foundations skill badge in the Asana Academy. You’ll learn more about how to write effective prompts, plan Smart workflows, and troubleshoot common issues.

Related articles

How to structure a prompt

Creating a clear prompt helps AI Studio understand exactly what you need and how it should deliver it. Use this simple and reliable four-part recipe for structuring prompts in AI Studio:

  1. Job to be done
  2. Context
  3. How to do it
  4. Examples

Below is an example of a prompt for a Smart workflow that uses Asana AI to analyze customer feedback. By including these four key points in your prompt, you'll be able to hit the ground running - even if you don't have much experience with prompt creation.

Job to be done

Start by clearly stating what you want the AI to do. This should be a concise statement that defines the core task. Often this will begin with the line “Your job is to…”

Try a simple, yet clear explanation like “Your job is to summarize customer feedback into actionable insights”.

Context

Provide background information about who the task is for and why it matters. This helps AI Studio understand the purpose and audience.

Try adding “This is for our product team’s monthly review meeting. These insights help the team prioritize feature development.” 

How to do it

Give specific instructions on how AI Studio should approach the task, and how you want the output to be delivered.

This might look something like “Categorize feedback by feature area, highlight recurring themes, and quantify sentiment when possible. Focus on actionable feedback rather than general praise or complaints.”

Optionally, you may find it helpful to include some of the following:

  • Guidelines to follow
    • “Use bullet points for each insight to improve readability”
  • Refinements to add flexibility
    • “If the feedback is too technical, simplify it for a non-technical audience”
  • Guardrails to limit responses
    • “Focus only on product feedback, not service or pricing complaints”
  • Do’s and don’ts
    • “Include direct quotes from customers"
    • "Do not include names”

Examples

Provide sample outputs to demonstrate to Asana AI exactly what you’re looking for. This can be especially helpful for complex or nuanced tasks.

Try adding something like "Here's what a good insight looks like: '27% of users mentioned difficulty finding the export function. Sample quote: I spent 10 minutes looking for the export button before giving up.'"

Related articles

Loading
How to structure prompts in AI Studio | Asana Help Center