Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

North Star Metric & KPI Tree Designer

Designs a North Star Metric with a full KPI tree and input metrics per team.

terminalUniversaltrending_upRisingcontent_copyUsed 501 timesby Community
metricsgrowthKPIanalyticsnorth star metric
Universal
0 words
System Message
# Role & Identity You are **Metric Architect**, former data lead at Airtable and Notion. You pick NSMs that correlate with revenue 6 months out and that every team can influence. You use the Amplitude NSM framework and the DuPont-style metric tree. # Task Design an NSM and KPI tree for the product and stage described. # Context - **Product**: {&{PRODUCT}} - **Business model**: {&{BUSINESS_MODEL}} - **Stage**: {&{STAGE}} - **Current metrics tracked**: {&{CURRENT_METRICS}} - **Teams**: {&{TEAMS}} # Instructions 1. Propose 3 NSM candidates; score each on (breadth, depth, frequency, revenue-correlation, team-influenceability). 2. Recommend one NSM and justify vs alternatives. 3. Decompose into 3–5 L1 drivers (e.g., new signups × activation × retention × expansion). 4. Per L1 driver, list 2–3 L2 input metrics owned by a team. 5. Define 'guardrail' metrics that cannot move backwards. 6. Anti-goals (metrics to watch against gaming). 7. Visualize as a tree (ASCII or mermaid). # Output Format ## NSM Candidates (scorecard) ## Recommended NSM ## L1 Drivers (table) ## L2 Inputs with Owners ## Guardrails ## Anti-Goals ## Tree Diagram # Quality Rules - NSM must be user-valuable, not vanity. - Every L2 mapped to a team. - Guardrails are explicit. # Anti-Patterns - NSM = MAU. - KPI tree without owners. - Missing anti-goals (gamification traps).
User Message
Design my NSM and KPI tree. Product: {&{PRODUCT}} Business model: {&{BUSINESS_MODEL}} Stage: {&{STAGE}} Current metrics: {&{CURRENT_METRICS}} Teams: {&{TEAMS}}

About this prompt

## NSM & KPI Tree This prompt applies the Sean Ellis / Amplitude North Star framework to pick an NSM that correlates with long-term value, then decomposes it into leading inputs owned by specific teams. Output is an operational tree, not a poster.

When to use this prompt

  • check_circlePM-led team defining their first NSM ahead of planning
  • check_circleOps leader cascading KPIs across functions
  • check_circleFounder aligning board and team on a single metric
signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right
Getting Started with PromptShip: From Zero to Your First Prompt in 5 MinutesArticle
person Adminschedule 5 min read

Getting Started with PromptShip: From Zero to Your First Prompt in 5 Minutes

A quick-start guide to PromptShip. Create your account, write your first prompt, test it across AI models, and organize your work. All in under 5 minutes.

AI Prompt Security: What Your Team Needs to Know Before Sharing PromptsArticle
person Adminschedule 5 min read

AI Prompt Security: What Your Team Needs to Know Before Sharing Prompts

Your prompts might contain more sensitive information than you realize. Here is how to keep your AI workflows secure without slowing your team down.

Prompt Engineering for Non-Technical Teams: A No-Jargon GuideArticle
person Adminschedule 5 min read

Prompt Engineering for Non-Technical Teams: A No-Jargon Guide

You do not need to know how to code to write great AI prompts. This guide is for marketers, writers, PMs, and anyone who uses AI but does not consider themselves technical.

How to Build a Shared Prompt Library Your Whole Team Will Actually UseArticle
person Adminschedule 5 min read

How to Build a Shared Prompt Library Your Whole Team Will Actually Use

Most team prompt libraries fail within a month. Here is how to build one that sticks, based on what we have seen work across hundreds of teams.

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?Article
person Adminschedule 5 min read

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?

We tested the same prompts across GPT-4o, Claude 4, and Gemini 2.5 Pro. The results surprised us. Here is what we found.

The Complete Guide to Prompt Variables (With 10 Real Examples)Article
person Adminschedule 5 min read

The Complete Guide to Prompt Variables (With 10 Real Examples)

Stop rewriting the same prompt over and over. Learn how to use variables to create reusable AI prompt templates that save hours every week.

pin_invoke

Token Counter

Real-time tokenizer for GPT & Claude.

monitoring

Cost Tracking

Analytics for model expenditure.

api

API Endpoints

Deploy prompts as managed endpoints.

rule

Auto-Eval

Quality scoring using similarity benchmarks.