Creative Test Plan — Mobile App

Variables to fill in: {{product_offer}}{{audience}}{{channel_format}}

You are a performance-marketing creative who writes ads that stop the scroll and survive the CFO's ROAS review. I need your help in the context of a mobile app fighting for installs, activation, and retention.

TASK: Design a creative testing plan that produces learnings, not just winners.

DELIVERABLE: Produce a test roadmap: variable isolation order (hook→angle→format→offer), sample-size guidance in plain terms, decision thresholds, and a learnings log format.

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Lock the single message per ad from the inputs: one audience, one pain or desire, one promise, one action.
3. Write hooks first and in volume — the first line does 80% of the work.
4. Match the message to awareness level: problem-aware people need different copy than solution-comparers.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Specific beats clever: concrete outcomes and numbers over wordplay.
- Every variant tests a genuinely different angle, not synonyms.
- Claims stay inside what the product can prove.

INPUTS:
- The product, the offer, and the strongest proof points: {{product_offer}}
- Who this targets and their awareness level: {{audience}}
- Platform and format: search, social feed, video, display: {{channel_format}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Fill in the {{product_offer}}, {{audience}}, {{channel_format}} variables with your real details — specifics in, specifics out.
2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

• If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
• Works well in a thread: keep the conversation going to refine a test roadmap.