VideoVideo variants and adaptationIntermediateDesigns a test

Video A/B test plan: variants that change one variable

Designs a creative test: one base video, single-variable variants, the constants to hold fixed, and an honest note on what the test can and cannot prove.

For: Paid social marketers, Creative strategists, Brand and content marketers · Works with: Any capable chat model (ChatGPT, Claude, Gemini, others)

Public beta. This prompt was drafted with AI assistance and checked by automated rules, but it has not been reviewed or tested by a person yet. Treat it as a starting point and check the output. It is hidden from search engines while in beta. Use the “Was this prompt useful?” box to tell us what works.

Your prompt

Act as a creative-testing strategist. Design an A/B test for a 15-second vertical video ad for a language-learning app aimed at adults 25-40 who want to learn Spanish on Meta Reels. Base video (describe it): A learner practises on the app during a commute, ends with a smile and a download CTA.. Variable to test: the first 3 seconds (hook). Create 3 variants that change ONLY that variable and keep everything else identical. For each, give the exact change and a hypothesis (label it a hypothesis). Then list: what must be held constant (audience, budget, placement, schedule, landing page, copy), how to name and track variants (UTM and ad-name convention), the primary metric and one secondary metric to decide on, and the decisions I must make before launch (duration, sample size inputs, stopping rule). Do not state a required sample size as fact; list the inputs that determine it and point me to a calculator. Finish with three reasons the test could be inconclusive. Do not predict a winner and do not invent benchmark numbers.

Customize

The fields start with example values so you can see how the prompt works. Everything stays in your browser.

Video format.

What is advertised.

Who it targets.

Where it runs.

Describe the base creative.

Exactly one element.

How many versions.

Example of what to expect

Illustrative only. It describes the kind of result this prompt aims for; real output varies by tool, model and run.

Three single-variable hook variants with hypotheses, a constants list, a naming and UTM scheme, primary and secondary metrics, pre-launch decisions and reasons the test might be inconclusive.

Expected format: Variant list, constants, tracking scheme, decisions, risks.

How to use it

  1. Run the variants with identical audience, budget and schedule.
  2. Use a calculator for sample size and significance.
  3. Document every variant's exact prompt and settings.

Limitations

  • Creative testing results are specific to your audience and moment; do not generalise from a single test.
  • The model cannot judge statistical power for you.

Platform notes

Any capable chat model (ChatGPT, Claude, Gemini, others)

Official docs read · checked 2026-10-11

Plain-text prompt for any chat model.

General notes on Any capable chat model (ChatGPT, Claude, Gemini, others)
  • These prompts are plain text and work in any chat assistant. For analytics prompts, paste a small, anonymised export; a chat model can misread columns or miscalculate, so recompute key numbers yourself.

Source, license and attribution

Origin
Original by MarketerTools
Publisher
MarketerTools
License
Original work by MarketerTools, free to copy and use. Informed by the linked documentation; no third-party text is reproduced.
Platform assumptions checked
2026-10-11

Documentation and references behind this prompt

These informed the structure and the platform notes. A reference is not a license, and no third-party prompt text is copied here.

Spotted an attribution error, or are you a source owner with a request? Use the chat button at the bottom right and quote prompt ID vid-035. We will correct or remove it.

Related prompts

  • VideoIntermediateWrites a set of prompts

    10 video hook ideas for one offer (text, not video)

    Generates ten distinct opening lines and first-shot ideas across different hook types, with each hook tied to a testable hypothesis.

    Any capable chat model (ChatGPT, Claude, Gemini, others)

  • ImageIntermediateWrites a set of prompts

    Creative test set: change one variable at a time

    Builds a fixed base prompt and a controlled list of variants that change exactly one element, so a creative test isolates what actually drove results.

    Any capable chat model (ChatGPT, Claude, Gemini, others)

  • AnalyticsIntermediateAnalyses your data

    A/B test result evaluation with statistical guardrails

    Interprets an A/B test from raw counts with checks for sample-ratio mismatch, peeking and practical significance, without inventing a significance result.

    Any capable chat model (ChatGPT, Claude, Gemini, others) · Google Sheets / Excel

  • VideoBeginnerGenerates a video

    Camera-movement test pack (same scene, one move changed)

    A fixed scene prompt with a single swappable camera move, for learning how your tool responds to each move before a real production.

    Google video models (Gemini Omni Flash, Veo 3.1) · Runway (Gen-4.5 and earlier) · Kling +2