How AI can help with: Vision

Creating the vision

As a Product Owner, an important part of your job is creating and adjusting your vision of the product you are responsible for. A vision is created by talking to customers, suppliers and colleagues, but also by looking into the data your product is collecting. AI can help to streamline this.

When using AI, it is good to follow best practices. For example, OpenAI explains how to best prompt GPT-5.

Talk to users

When talking to users, create a format you can reuse for each conversation. Not only will it help you structure the conversation, it will make it easier for AI to analyse the data.

For example, before the conversation:

• Define the goal: what are you trying to learn?
• Know the user: review the customer's profile, look at their usage data and potential previous feedback

Then, create a set of open ended questions you can use during the conversation. Only use this as a guide and dive deeper into specific topics if you deem fit.

Either take notes during the conversation, or ask the user whether you can record the conversation. If allowed, you can use a voice-to-text AI model to transcribe the conversation. There are many websites where you can transcribe for a small fee.

Then, put use the following prompt to analyse the conversations. We also provide an example result, so the AI better understands what we are expecting.

# Identity

You are a product analysis assistant that transforms raw user conversations into actionable product insights, helping a product owner discover pain points, opportunities, and next steps.

# Instructions

* Redact any personal identifiers (e.g., emails, phone numbers).
* Extract primary/secondary intents, jobs-to-be-done (JTBD), key pain points, opportunities, sentiment, urgency, and actionable next steps.
* Support every insight with at least one verbatim quote.
* Score opportunities with ICE (Impact, Confidence, Ease) and compute a priority number = (Impact × Confidence) + Ease.

# Examples
<conversation id="example-1">
User: I tried exporting my dashboard to CSV, but it times out after a minute. I only need last month's data.  
Agent: Sorry about that. Are you filtering by date?  
User: Yes, but our account has 200k rows. I just want a quick summary.  
Agent: We can run it overnight.  
User: That won't work—I have a weekly report due in an hour.
</conversation>

<assistant_response id="example-1">
Summary  
• Export flow times out on large datasets; needs fast last-month summary export within 1 hour.  
• Sentiment: Negative  
• Urgency: High

Intents  
• Primary: Export last month's dashboard quickly  
• Secondary: Get summarized data without full export

Jobs-to-Be-Done  
• When preparing weekly reports, I want to export last month quickly so I can meet deadlines.  
• Success criteria: Export completes in under 30 seconds.

Pain Points  
• Performance: "it times out after a minute"  
• Usability: "I only need last month's data... quick summary"

Opportunities  
• O1 – Impact 5, Confidence 4, Ease 4, Priority 24: Add scoped export (Last 30 days + aggregated summary).  
• O2 – Impact 4, Confidence 3, Ease 2, Priority 14: Async export with email notification for large jobs.

Next Steps  
• Product: Define export presets and metrics.  
• Engineering: Implement pre-aggregation and timeout guard.  
• Design: Add quick export UI control.

Key Quotes  
• "I only need last month's data."  
• "That won't work—I have a weekly report due in an hour."
</assistant_response>

Find out what your competitors are doing

Another way to get ideas what to build, is looking at competitors. Although you should never copy a competitor's functionality one-on-one (as everyone's context is different), it can give you ideas.

ChatGPT's new agent mode can really help to quickly perform market/competitor research. Find the competitors you are most interested in, open up chatgpt and select Agent mode.

I use the following prompt structure for these use cases:

"I am working at [name and url of your company], we help [explain what your company is doing]. We have a couple of main competitors, like [list your competitors]. Find out [mention what you are interested in]. Summarize your findings and write down all the takeaways for my company.

I am working at [name and url of your company], we help [explain what your company is doing]. We have a couple of main competitors, like [list your competitors]. Find out [mention what you are interested in]. Summarize your findings and write down all the takeaways for my company.

I also often look at competitor's open vacancies, as companies often tell future employees what they will be working on/what their vision is. You can include this in the prompt as well:

I am working at [name and url of your company], we help [explain what your company is doing]. We have a couple of main competitors, like [list your competitors]. Find out [mention what you are interested in]. Summarize your findings and write down all the takeaways for my company. Also search through the companies open vacancies to find interesting information.