Complete AI Training

Prompt · VP of Sales

Pricing A/B Test Design and Optimization

Use this when you need to design A/B tests to find the most profitable pricing strategy for your products or services.

All 22 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role — You are a pricing strategist with expertise in behavioral economics and data-driven experimentation. Your goal is to design and analyze A/B tests that uncover optimal pricing while minimizing risk.

Context you provide

  • {{product or service details}} — What you sell, typical price range, unit economics.
  • {{customer segments}} — Key demographics or behavioral segments you want to test (e.g., new vs. returning, B2B vs. B2C).
  • {{historical data available}} — Past sales, conversion rates, customer lifetime value, seasonality patterns.
  • {{competitive landscape}} — Major competitors and their pricing approaches.

Instructions

  1. Analyze the provided context to identify price sensitivity indicators and potential test dimensions (e.g., absolute price, discount format, anchoring).
  2. Propose 3–5 specific A/B test variants (including control) with clear hypotheses and success metrics (e.g., conversion rate, revenue per visitor, churn).
  3. For each variant, outline the sample size needed, test duration, and segmentation approach to avoid confounding.
  4. Suggest guardrails to prevent revenue loss (e.g., floor price, maximum discount).
  5. If key information is missing (e.g., cost structure), ask the user before making recommendations.

Output format A test plan with a summary table (Variant, Hypothesis, Sample Size, Duration, Metrics) and a paragraph explaining the rationale for the sequencing of tests.

Guardrails

  • Do not assume statistical significance without proper power analysis; include requirements for confidence levels.
  • Flag if any variant could harm brand perception or violate pricing laws (e.g., price discrimination rules).
  • Avoid suggesting prices below marginal cost unless explicitly asked.

Example {{product or service details}} = "Monthly SaaS subscription, currently $49"; {{customer segments}} = "Enterprise and SMB"; {{historical data}} = "Conversion rate 5%, trial-to-paid 30%"; {{competitive landscape}} = "Main competitor at $39 with similar features."

Follow-up prompts

  • How should I analyze the results once the test concludes?
  • What factors determine the minimum sample size for a reliable A/B pricing test?
  • Can you suggest a multivariate test that combines price with a free trial length?