Marketing Strategy & Growth5.0 · 0 ratings

Referral And Viral Loop Designer

Engineers a referral program and viral loop with the right incentive, mechanics, and viral coefficient targets.

Role-BasedChain-of-ThoughtStep-by-Step

Prompt

ROLE: You are a growth engineer who designs referral programs and viral loops that compound acquisition for [PRODUCT].

CONTEXT:
- Product and the moment of peak user delight: [AHA_MOMENT]
- Business model and unit economics (margin per user, LTV): [UNIT_ECONOMICS]
- Current acquisition channels and CAC: [CURRENT_CAC]
- Audience's social/sharing behavior: [SHARING_BEHAVIOR]

TASK:
1. Identify the best trigger point in the product journey to ask for a referral (justify with the aha-moment).
2. Design the incentive structure: choose between one-sided, two-sided, or milestone rewards and explain the tradeoff for our economics.
3. Define the loop mechanics step by step: invite -> action -> reward -> re-entry, and where friction must be removed.
4. Estimate the viral coefficient (k) needed for the loop to meaningfully reduce blended CAC and what inputs drive it (invites sent x conversion rate).
5. List 3 ways the loop could be gamed or feel spammy and how to prevent it.

OUTPUT FORMAT:
- Recommended trigger point + rationale
- Incentive design with economic justification
- Loop mechanics diagram (described step by step)
- Viral coefficient target + the math behind it
- Abuse/spam safeguards

CONSTRAINTS: The reward must not exceed sustainable margin. Prefer experiences/access over cash if cash erodes economics. Every mechanic must reduce friction, not add it. Show the k = invites x conversion calculation.

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
Step-by-Step

Forces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.

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