Skip to main content
ResearchAdvanced

Experiment Design Review Rubric

Review a proposed A/B test before it gets traffic: pin the design down, run honest power and interference math with the assumptions attached, score it on a weighted validity rubric with hard gates, and hand back the required fixes plus a filled pre-registration record. Works in any chat model — no connected tools needed.

A 4-step agentic workflow pack for research built to run with ChatGPT, Claude, and Gemini. Open the Markdown files, fill the variables, and paste into your model. Most buyers get a reviewable result in about 45 minutes.

  • Turn a prose experiment proposal into a sixteen-field design spec where every silence is registered instead of charitably filled in
  • Catch the twelve practices that manufacture false wins — peeking without a sequential correction, metric switching, post-hoc segment mining, uncorrected multiple comparisons, underpowered nulls read as no effect
  • Run sample-size and duration math that ships its assumption ledger with it, plus the multipliers for unequal splits, clustering, dilution, variance reduction and sequential designs
  • Test whether the minimum detectable effect came from the decision or was reverse-engineered from whatever traffic was available
  • Work an interference taxonomy — marketplace competition, social spillover, shared budgets, shared models, cross-device identity — and cost each remedy with its design effect
  • Score eight weighted validity dimensions with explicit 1-5 anchors and six hard gates that cap the verdict no matter how high the total
  • Hand back a ranked fix list separated into blockers and before-launch work, plus a filled pre-registration record the proposer pastes straight into the design doc
CChatGPTClaudeClaudeGeminiGemini
promptscart.com / prompt-packs / experiment-design-review-rubric
Run in
ChatGPT · Claude +1
Your AI model
Step 1
Design Intake & Falsifiability Audit
Paste the experiment proposal you were asked to review — design doc, ticket, or setup screen — plus context on the surface and who uses it, and your team's experimentation standard if you have one
Step 2
Power, MDE & Interference Check
Paste the design spec from the intake step plus a traffic export you already have — eligible units per week, baseline rate or mean, variance for continuous metrics — and what your experimentation platform supports
Step 3
Validity Threat Scorecard
Paste the intake findings and the power and interference findings, plus the analysis or stopping plan if it lives in a separate doc or in your platform's configuration
Step 4 · optional
Pre-Launch Fix List & Registration Record
Paste the design spec, the scorecard verdict, and the power and interference findings, plus who owns what and how far out launch is planned
Output
Your deliverable
Copy-paste ready
One-time
$10
~45 min
to first result

Prompt Customization Serviceoptional help adapting variables and output to your brand voice. Choose your tier at checkout (not tied to this prompt's price).

Instant download after payment
Refund as per the Refund Policy.
Email Support · 24h SLA
Lifetime updates

Models supported
C ChatGPTClaude ClaudeGemini Gemini
Best valueSave $1389
Get this pack + 168 more in the Lifetime Bundle

This pack is $10 on its own. Buying every pack separately costs $1538. The Lifetime Bundle is $149 one-time — you save $1389 (90% off) and unlock every future pack free.

Get the Lifetime Bundle — $149
Already purchased?
Download Experiment Design Review Rubric

Paste the license key from your receipt. It must match this prompt pack.

What ships with your purchase

Prompt files

Plain Markdown files with `{{variables}}` you fill in, ready to paste into ChatGPT, Claude, or Gemini. No setup, no tooling required.

Usage guide

Variable reference, model compatibility, examples, and customization tips so you can adapt the pack to your brand voice.

Lifetime updates

When we improve the pack, you get the new version automatically. Email support included with every purchase.

Works with: ChatGPT, Claude, Gemini.

The workflow inside this pack

4 composable prompts you run in order — each one picks up where the last left off.

  1. Step 1

    Design Intake & Falsifiability Audit

    Paste the experiment proposal you were asked to review — design doc, ticket, or setup screen — plus context on the surface and who uses it, and your team's experimentation standard if you have one

  2. Step 2

    Power, MDE & Interference Check

    Paste the design spec from the intake step plus a traffic export you already have — eligible units per week, baseline rate or mean, variance for continuous metrics — and what your experimentation platform supports

  3. Step 3

    Validity Threat Scorecard

    Paste the intake findings and the power and interference findings, plus the analysis or stopping plan if it lives in a separate doc or in your platform's configuration

  4. Step 4 · optional

    Pre-Launch Fix List & Registration Record

    Paste the design spec, the scorecard verdict, and the power and interference findings, plus who owns what and how far out launch is planned

Perpetual (lifetime) use license

Your one-time purchase includes an ongoing right to use this prompt pack with the AI tools and models you control for your own and your clients' work — not for resale or public redistribution of the files as a product.

We keep the copyright

The prompt files, guides, examples, and bundled assets stay our copyrighted works (or our licensors'). Payment grants the limited license in our Terms only — it does not transfer ownership.

Need help adapting this prompt to your team? Add Prompt Customization Service at checkout.

FAQ

How long does it take to use Experiment Design Review Rubric?
Most buyers finish in a few minutes: open the prompt file, fill the variables, and paste into your model. The first run is the slowest because you decide variable values; reuse is instant.
What if I get stuck?
Email support@promptscart.com. Free basic support is included with every purchase, and you'll get a reply from our team within 24 hours. If you need help adapting variables or output, we can schedule a call.
Do I need a paid plan with ChatGPT?
The prompt works on free tiers of ChatGPT, Claude, and Gemini. Heavy use can hit free-tier limits; paid plans get longer context and faster responses, but the prompt itself is the value.
Can I customize the prompt?
Yes, completely. You own the prompt files: edit the role framing, add variables, swap output sections, fork it to match your brand voice. Support can help you plan customizations over email.
What if it doesn't work for me?
Refund as per our Refund Policy (https://promptscart.com/refund-policy). Or add Prompt Customization Service at checkout for help adapting variables and output to your workflow.