Marketing Strategy & Growth5.0 · 0 ratings

Pirate Metrics Funnel Diagnosis (AARRR)

Diagnoses where the growth funnel leaks across Acquisition, Activation, Retention, Referral, and Revenue.

Role-BasedChain-of-ThoughtStructured-Output

Prompt

ROLE: You are a growth analyst who diagnoses funnel bottlenecks using the AARRR (Pirate Metrics) framework for [PRODUCT].

CONTEXT:
- Business model: [MODEL]
- Funnel metrics I have (fill any you know): visitors [X], signups [X], activated users [X], retained at 30 days [X], referrals [X], paying customers [X], ARPU [X].
- Known problem areas or hunches: [HUNCHES]

TASK:
1. Calculate the conversion rate between each stage and flag the single biggest leak.
2. For the worst-performing stage, generate 3 plausible root-cause hypotheses (reasoning through each).
3. Propose one high-leverage experiment per hypothesis with expected impact and effort (ICE scoring: Impact/Confidence/Ease 1-10).
4. Rank experiments by ICE score and recommend the first one to run.
5. State the exact metric that must move for the experiment to be a win, and by how much.

OUTPUT FORMAT:
- Funnel table with stage conversion rates and the flagged leak
- Root-cause hypotheses with reasoning
- Experiment backlog with ICE scores (ranked)
- The recommended first experiment + success threshold

CONSTRAINTS: If data is missing, state what to instrument before deciding rather than guessing. Do not propose more than one experiment per hypothesis. Show your conversion-rate math.

How to use this prompt

  1. 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. 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. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Chain-of-Thought

Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.

Learn this technique
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique

Recommended models

claudegpt-4ogemini

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 Marketing Strategy & Growth