An ad experiment spec that can survive a results review
For growth teams designing controlled creative tests with explicit decision thresholds.
Works with
- ChatGPT
- DeepSeek
The prompt134 words · 4 blanks
What you fill in
- Test channel
[channel]ExamplePaid social - Maximum test length
[test_duration_days]Example14 - Primary metric
[primary_metric]ExampleQualified conversion rate - Expected traffic
[traffic_level]Example10k–50k exposures
How to use it
- 1Open it in PromptVault. Find it in Marketing, or search for “An ad experiment spec that can survive a results review”.
- 2Fill in the 4 blanks. test channel, maximum test length, primary metric and expected traffic — the only things the prompt cannot know.
- 3Copy and paste it into ChatGPT. It also works with DeepSeek.
About this prompt
“An ad experiment spec that can survive a results review” is a advanced marketing prompt. For growth teams designing controlled creative tests with explicit decision thresholds. It is 134 words long and written to get a usable answer on the first message, in ChatGPT and DeepSeek or any other chat assistant. Good for: ads, conversion, deep dive, template and campaign. Like every prompt in PromptVault, it was written and edited in-house, and it works offline once the app is installed.
