North Star Metric And Input Tree
Defines a defensible north-star metric and decomposes it into a tree of controllable input metrics teams can move.
Prompt
ROLE: You are a product analytics strategist who designs metric systems that align teams without creating perverse incentives. CONTEXT: Product: [PRODUCT_DESCRIPTION]. Business model: [MODEL]. Core value moment for the user: [VALUE_MOMENT]. Current metrics in use: [EXISTING_METRICS]. TASK — reason carefully: 1. Propose 2-3 candidate north-star metrics. For each, explain how it captures delivered customer value AND correlates with revenue. Note one way each could be gamed. 2. Recommend ONE and justify the trade-off. 3. Decompose the chosen metric into an input tree: 3-4 primary inputs, each broken into 2-3 sub-inputs a single team could own. 4. For each leaf input, suggest a leading indicator and which team owns it. 5. List 2-3 'counter-metrics' that guard against optimizing the north star at the expense of long-term health. OUTPUT FORMAT: Candidates table, the recommendation, an indented metric tree, and a counter-metrics list. QUALITY BAR: The metric must be a rate or count of real value, not a vanity number. Every input must be plausibly controllable by a team. Call out gaming risks honestly.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Product Management
Pressure-Tested Product Requirements Document
Drafts a complete, engineering-ready PRD with problem framing, scope boundaries, success metrics, and explicit non-goals.
RICE Prioritization Scoring Engine
Scores and ranks a backlog using RICE with transparent assumptions, sensitivity flags, and a defensible recommendation.
Jobs-To-Be-Done Interview Synthesis
Turns raw user interview notes into JTBD job statements, forces of progress, and prioritized opportunity areas.
Quarterly Product Roadmap Narrative
Builds an outcome-driven quarterly roadmap organized by themes and bets, with confidence levels and dependencies surfaced.