Data Analysis

Design indicator boards that truly support decision-making

Define indicator trees, calibers, refresh frequencies, alarms, and drill-down paths based on user decisions.

Complete prompt

You are a business data product manager. Please design a set of decision-making indicator boards.

Business goal: [target]
Kanban user: [role]
The decision they need to make: [decision list]
Existing data and indicators: [Data situation]
Update frequency: [Real time/Daily/Weekly/Monthly]

Output: North Star indicators and indicator tree, business definition and calculation caliber of each indicator, dimensions and filters, default time window, target value or benchmark, abnormal threshold, drill-down path, recommended chart, data delay and quality tips.

Design information levels based on first-screen overview, problem diagnosis, and detailed tracking. Each chart explains what decision it supports; remove metrics that only display but do not trigger action.

Example output

Above the fold: New MRR, net revenue retention, customer acquisition cost, payback cycle.
Diagnosis: Split conversion funnel by channel and package; split churn by customer size.
Alert: Net revenue retention is below target for 7 consecutive days, triggering drill-down to downgrade and cancellation reasons.

USAGE GUIDE

When to use it

Define indicator trees, calibers, refresh frequencies, alarms, and drill-down paths based on user decisions. Use it as a structured starting point, then review the result against your original material.

How to fill the variables

target: Add concrete facts, context, and constraints. Mark unknown details instead of guessing.
role: Add concrete facts, context, and constraints. Mark unknown details instead of guessing.
decision list: Add concrete facts, context, and constraints. Mark unknown details instead of guessing.
Data situation: Add concrete facts, context, and constraints. Mark unknown details instead of guessing.
Real time/Daily/Weekly/Monthly: Add concrete facts, context, and constraints. Mark unknown details instead of guessing.

Get better results

Describe the audience and intended decision.
Include source material and hard constraints.
State what the model must not invent.

Before you use the output

Verify facts, numbers, and quotations.
Check that uncertainty is clearly labeled.
Test or review high-impact recommendations.

Editorial note: This template has been structured for practical use. Results vary by model and input; verify important outputs against primary sources.