Skip to content
New this week26 prompts for Sora, Veo and Runway video workflows.
Explore video prompts→
AIPrompt123Prompt library

Search AIPrompt123

Search prompts, categories, platforms and repositories

Design an A/B test

This copy-ready data analysis prompt helps you design an A/B test with fewer blank-page decisions. Paste it into Claude and ChatGPT, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.

4.8(57 ratings)607 copies
Updated By Author
41 words · v1.2

Fill in the blanks · 2 variables

Claude promptReplace every highlighted token before sending
<task>
Design an A/B test for {hypothesis}. Specify the unit of randomisation, primary metric, guardrail metrics, minimum detectable effect, sample size logic, duration and stopping rule. Identify the biggest validity threat and how to monitor it. Do not suggest peeking.

Context:
{context}
</task>

Think carefully before answering. Keep any reasoning separate and put the final deliverable inside <answer> tags.
Open in Claude

Comments

Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.

Saved with an anonymous browser ID. No login needed.

How to use this prompt

  1. 1

    Open Claude and start a new chat. Paste the prompt exactly as written.

  2. 2

    Replace each placeholder ({hypothesis}, {context}) with your own details. Leave the instructions and the output format untouched.

  3. 3

    Add one concrete example or data point if the model's first answer is vague. Specific input produces specific output.

  4. 4

    Run it once, then ask for a single revision with a specific critique rather than regenerating from scratch.

  5. 5

    Review the result. Reconcile totals to a trusted source, verify the query and review the statistical claim with an analyst.

Worked example

This is the kind of input the prompt expects and the shape of output it produces. Your result will differ with the model and the details you supply.

Example input

Hypothesis: a shorter onboarding increases activation Context: Add the relevant business or project context.

Example output

**Finding:** activation within 7 days predicts 90-day retention, but the effect is concentrated in self-serve signups. **Method:** cohort by signup month, activation defined as completing two core actions within 7 days, retention measured on day 90. Excludes internal accounts and trials. **Caveat:** sales-assisted accounts are small and may be underpowered. This is correlational, not causal. **Sanity check:** total users reconcile to the billing table within 0.4%.

Tips for a better result

  • Give the schema and the metric definition before asking for an interpretation.
  • Ask for the query or code so you can rerun it and check a known total.
  • Require a 'what this cannot tell us' section to surface confounders.
  • Change one variable at a time and compare the outputs; it is the fastest way to learn what this model responds to.

Common mistakes

  • Trusting a percentage without checking the denominator or sample size.
  • Treating correlation as causation in a retention or revenue analysis.
  • Letting the model invent a result for data it was not given.
Verified Knowledge · FAQ

Questions about this prompt

Practical answers about running the design an a/b test prompt.

Related prompts

Same job, a different angle — or the next step in the workflow.

Data Analysis
Intermediate

Turn a dashboard request into a spec

A data analysis prompt for turn a dashboard request into a spec. It gives ChatGPT and Claude a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.

ChatGPTClaude
4.7(65)627 copies
Data Analysis
Intermediate

Compare two periods fairly

Compare two periods fairly with a prompt built for Claude and ChatGPT. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.

ClaudeChatGPT
4.9(70)584 copies

Investigate a metric drop

Investigate a metric drop with a prompt built for Claude and ChatGPT. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.

ClaudeChatGPTPerplexity
4.8(63)666 copies

Written and reviewed by Author

AIPrompt123 Contributor

Contributing author and prompt engineer at AIPrompt123.

Last reviewed 28 April 2026 · version 1.2 · tested on Claude, ChatGPT