Turn a vague stakeholder request into a clear problem statement
A one-page problem brief that separates the ask from the underlying need, before anyone commits to a solution.
The prompt
Help me turn a stakeholder request into a clear problem statement before we discuss solutions.
The request as I received it: [PASTE OR PARAPHRASE - e.g. "We need a bulk export button"]
Who asked and their role: [NAME/ROLE, TEAM]
What I know about why they want it: [CONTEXT, COMPLAINTS, DEALS, INCIDENTS]
Who would be affected: [USER TYPES, SEGMENTS]
Evidence I have: [TICKETS, DATA, QUOTES - or "none yet"]
Steps:
1. Restate the request as a solution, then work backward to the problem it is trying to solve. Offer 2-3 possible underlying problems if it is ambiguous.
2. Ask me the 5-8 questions I should put to the requester to confirm which problem is real (who, how often, what they do today, what it costs them).
3. Draft the problem brief.
Problem brief format:
- Problem statement (one sentence: [user] struggles to [job] because [obstacle], which causes [consequence]).
- Who has this problem and how often.
- Current workaround and its cost.
- Evidence so far, and the evidence still missing.
- Why now.
- What success would look like (an outcome, not a feature).
- Out of scope.
Rules: do not propose a solution in the brief. Do not invent numbers; mark gaps as [ADD DATA] or [CONFIRM WITH REQUESTER]. Keep the brief under 300 words.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Product & UX Design prompts
What to fill in
- PASTE OR PARAPHRASE - e.g. "We need a bulk export button"
- NAME/ROLE, TEAM
- CONTEXT, COMPLAINTS, DEALS, INCIDENTS
- USER TYPES, SEGMENTS
- TICKETS, DATA, QUOTES - or "none yet"
- user
- job
- obstacle
- consequence
- ADD DATA
- CONFIRM WITH REQUESTER
How this prompt is built
This prompt follows the RTF structure (Role, Task, Format). RTF tells the model who to be, what to do and what shape the answer should take. It is the quickest structure that still gives noticeably better results than a bare request.
Related prompts
- Get interviewed to turn a rough idea into a specThe AI interviews you, one question at a time, until your idea becomes a clear specification.
- Resolve conflicting stakeholder feedback on a designSorts contradictory feedback from different stakeholders into the real underlying concerns, options, and a reply that moves to a decision.
- Turn research insights into problem statements and How Might We questionsConverts research findings into sharp problem statements and well-scoped How Might We questions ready for an ideation session.
- Prioritize a product roadmap or backlogScores and orders features with a transparent model (RICE, value vs. effort) and builds a roadmap.