Prompt: Campaign Strategy – A/B Testing

Context: I’m planning A/B tests for [insert campaign type] at [insert company name] to improve [insert specific metrics – conversion rate/click-through rate/engagement]. Our current performance baseline is [insert current metrics] and we want to achieve [insert goal/target improvement]. We have [insert traffic volume/audience size] to work with and [insert testing timeframe] to run experiments.

Role: Act as a data-driven marketing strategist with expertise in conversion rate optimisation and statistical testing, particularly experienced in [insert relevant channel/industry] campaign optimisation.

Examples: Structure this testing plan like [insert example of thorough testing methodology], which systematically tests one variable at a time with clear success metrics. Focus on statistically significant sample sizes and practical business impact like their approach to [insert specific testing example].

Action: Develop a comprehensive A/B testing plan that includes:

  • [insert number] specific test hypotheses with rationale
  • Variable isolation strategy (what to test and why)
  • Sample size calculations for statistical significance
  • Testing timeline and sequencing
  • Success metrics and measurement framework
  • Implementation requirements and resource needs

Tone: Analytical and methodical, focused on data-driven decisions rather than assumptions. Professional and detailed, ensuring stakeholder confidence in the testing approach.

Output Format:

  • Executive summary of testing strategy
  • Individual test plans with hypothesis, variables, and metrics
  • Sample size and duration calculations
  • Testing calendar with dependencies
  • Implementation checklist for each test
  • Reporting template for results analysis
  • Decision framework for implementing winning variations

Refinement:

  • Ensure each test can achieve 95% statistical confidence
  • Plan for minimum [insert duration] day testing periods
  • Account for external factors (seasonality, campaigns, etc.)
  • Include budget requirements for each test
  • Plan for both positive and negative results
  • Consider technical implementation complexity
  • Include stakeholder communication plan
  • Design for iterative learning and continuous optimisation