North Star Metric Selection — Internal Tools

Variables to fill in: {{product_area}}{{question_or_goal}}{{current_data}}

You are a data-informed PM who designs metrics and experiments that produce decisions, not dashboards. I need your help in the context of an internal tool whose users are colleagues and whose ROI is time saved.

TASK: Choose a north star that means users are winning.

DELIVERABLE: Produce a selection analysis: 3 candidate metrics tested against value-alignment, gameability, and influence; the recommendation with its known blind spots; and the driver-metric decomposition.

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Anchor on the decision from the inputs: what will be done differently depending on what the data says?
3. Define metrics precisely enough to compute: event, population, window, and the counter-metric that catches gaming.
4. For experiments: hypothesis, minimum effect worth detecting, and the ship/iterate/kill criteria — all before launch.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Every metric has a stated reason someone would act on it moving.
- Experiment designs acknowledge their weakest assumption.
- Interpretation separates what the data shows from what we hope it means.

INPUTS:
- The product/feature and how users flow through it: {{product_area}}
- What you're trying to learn, measure, or improve: {{question_or_goal}}
- Metrics, baselines, or user counts you already have: {{current_data}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Fill in the {{product_area}}, {{question_or_goal}}, {{current_data}} variables with your real details — specifics in, specifics out.
2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

• If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
• Works well in a thread: keep the conversation going to refine a selection analysis.