Build a KPI tree from a top-level business goal
Before you build a dashboard, you need to know which metrics actually connect to the goal you care about. This prompt constructs a structured KPI tree that shows drivers, lag and lead indicators, and data-source requirements.
You are a strategic analytics consultant. I need to build a KPI tree that connects a top-level business goal to the specific metrics my team should track and own.
Business goal: {{BUSINESS_GOAL}}
Business model context (e.g., SaaS, marketplace, e-commerce, media): {{BUSINESS_MODEL}}
Teams that will use this KPI tree: {{TEAMS}}
Time horizon for the goal: {{TIME_HORIZON}}
Follow these steps:
1. Restate the top-level goal as a single, measurable North Star metric with a clear unit (e.g., monthly recurring revenue in USD, weekly active users).
2. Decompose the North Star into 3–5 Level 2 driver metrics. For each, explain the causal link to the North Star in one sentence.
3. For each Level 2 driver, list 2–3 Level 3 input metrics (the levers teams can actually influence week to week).
4. For each metric at all levels, note: (a) whether it is a lead or lag indicator, (b) the likely data source, and (c) the team responsible.
5. Flag any driver metric that is important but likely difficult to measure with standard tooling, and suggest a proxy.
6. Identify one metric at each level that is commonly tracked but is actually a vanity metric for this specific goal — and explain why.
Format the output as an indented outline, not a prose paragraph. {{BUSINESS_GOAL}}{{BUSINESS_MODEL}}{{TEAMS}}{{TIME_HORIZON}}
How to use this prompt
- Copy the prompt above (Copy button on the top-right).
- Replace each
{{VAR}}with your own value. Variables:{{BUSINESS_GOAL}}{{BUSINESS_MODEL}}{{TEAMS}}{{TIME_HORIZON}}. - Paste it into one of the recommended tools below.
- Iterate: tighten constraints in the prompt if the output is generic.
Why this prompt is structured this way
The prompt is split into explicit steps because LLMs do better when the path is named, not implied. Each variable forces specificity at the input layer — vague inputs get vague outputs.
Pair this prompt with a tool
Notion AI
$8/user/mo add-onAI baked into the docs/wiki/projects tool you already use.
Notion AI is unremarkable as a standalone writer but indispensable if Notion is your team's source of truth — it works on the docs and databases you already have.
Perplexity
$0/mo (Pro at $20)AI search engine with citations.
Perplexity is the answer engine Google would build if it weren't protecting search ad revenue. Cited answers, follow-up questions, focused source modes.
Claude (Anthropic)
$0/mo (Pro at $20)Frontier model with long context and strong reasoning.
Claude (Opus / Sonnet / Haiku tiers) is the assistant favored by writers and engineers who care about reasoning quality and tone. 1M token context on Opus.
ChatGPT (OpenAI)
$0/mo (Plus at $20)The category-defining general-purpose AI assistant.
ChatGPT has the broadest feature surface: image gen, voice, custom GPTs, web browsing, code execution. Often the right default; sometimes beaten on specific tasks by Claude or Perplexity.
The PlaybookPrompts weekly
One short email per week. The five sharpest prompts we found, one tool worth your attention, one anti-pattern to avoid. Unsubscribe in one click.
Newsletter signup is not configured. Set PUBLIC_NEWSLETTER_USERNAME in the build env.