Turn Customer Feedback into Prioritized User Stories
Talking to customers is one of the best ways to understand what they truly need—but turning pages of notes into actionable backlog items can be time-consuming. This workflow helps you move from raw customer conversations to prioritized user stories faster, while ensuring important insights don't get lost along the way.
📌 Before You Start
The AI tools featured in this workflow are examples, not requirements. Every organization has different approved tools, security policies, and ways of working.
The goal of AI Toolsday isn't to recommend one specific product—it's to share practical AI workflows that you can adapt using the tools available to you. If your organization uses Microsoft Copilot, Google Gemini, Claude, ChatGPT Enterprise, or another approved AI solution, feel free to substitute those where it makes sense.
Focus on the workflow, not the tool.
🛠️ Tools Used
Fathom
Capture and transcribe customer conversations automatically so you can focus on listening instead of taking notes.
NotebookLM
Analyze multiple customer interviews together, identify recurring themes, and ground insights in the actual conversations rather than assumptions.
ChatGPT
Transform those insights into well-structured user stories, acceptance criteria, and backlog-ready work items.
Jira (or Azure DevOps)
Review, refine, and prioritize the stories with your Product Owner before adding them to the backlog.
⚙️ How It Works
Step 1: Capture the conversation
Record your customer interviews using Fathom (or another meeting transcription tool). Instead of worrying about writing everything down, focus on asking thoughtful follow-up questions and understanding the customer's experience.
Once your interviews are complete, export the transcripts.
Step 2: Look for patterns with NotebookLM
Upload several interview transcripts into NotebookLM. Rather than analyzing each interview individually, NotebookLM excels at finding common themes across multiple conversations.
Try asking questions like:
- What pain points came up most frequently?
- Which requests were mentioned by multiple customers?
- What frustrations seem to have the biggest business impact?
- What assumptions did we make that customers challenged?
- Are there any surprising patterns across these interviews?
The goal isn't to identify individual feature requests—it's to understand the underlying customer problems.
Step 3: Turn insights into backlog items with ChatGPT
Once you've identified the major themes, copy NotebookLM's findings into ChatGPT.
Ask it to:
- Group similar customer needs
- Generate acceptance criteria
- Suggest priorities based on customer impact
- Highlight questions that should be answered during backlog refinement
ChatGPT does a great job of transforming research into structured, actionable work your team can discuss.
Step 4: Review with your team
AI should accelerate the first draft—not replace product thinking.
Review the generated stories with your Product Owner and team. Validate that they accurately represent the customer problem, refine acceptance criteria, and prioritize them alongside your existing backlog.
💡 Why Agile Pros Care
Customer interviews often generate dozens of pages of notes, making it easy for valuable insights to get buried. This workflow helps Product Managers, Product Owners, and Agile teams quickly identify recurring customer needs and turn them into actionable backlog items.
Instead of spending hours sorting through transcripts, your team can spend that time discussing solutions, making trade-offs, and delivering value.
💬 Prompt to Copy
You are an experienced Product Manager working within a SAFe environment.
Review the customer interview insights below and identify the most significant customer problems. Group similar feedback into themes, then create backlog-ready user stories using the format:
As a...
I want...
So that...
For each story, also provide:
- Any assumptions that should be validated
- Questions to discuss during backlog refinement
- A suggested priority (High, Medium, Low) based on customer impact
Finally, summarize the top three customer themes that should influence future product decisions.
Customer Interview Insights:
Paste your NotebookLM summary here.
✅ Try It This Week
Have customer interview notes sitting in a folder? Upload two or three recent conversations into NotebookLM and ask it to identify recurring customer pain points. Then use ChatGPT to draft user stories from those insights and compare them to the stories you would have written yourself.
💬 Continue the Conversation
How does your team currently capture and organize customer feedback? Have you found an effective way to ensure those insights make it into your backlog?
🤝 AI Toolsday Tip
⚠️ AI works best as a collaborative partner—not a replacement for your expertise. Always review AI-generated outputs to ensure they accurately reflect your team's context, customer needs, and organizational goals.
