Ad Copy Testing Framework With Variants
Plan structured copy tests and write the variants.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Plan structured copy tests and write the variants. Product and offer: [PRODUCT_AND_OFFER]. Audience: [AUDIENCE]. Platform and format limits: [PLATFORM_AND_LIMITS]. Current best ad and results: [CURRENT_BEST_AD]. Budget per test: [TEST_BUDGET]. Claims allowed and not allowed: [CLAIM_RULES].
Return valid JSON only, in this shape:
{"hypotheses": [{"id": "H1", "statement": "If we lead with the time saved instead of the price, click-through rate will rise because ...", "variable": "angle", "metric": "click-through rate", "minimum_runtime_days": number, "approx_impressions_needed_per_variant": number, "decision_rule": "..."}],
"control": {"headline": "...", "primary_text": "...", "cta": "..."},
"variants": [{"id": "V1", "hypothesis_id": "H1", "changes_only": "headline", "headline": "...", "primary_text": "...", "cta": "...", "within_character_limits": true, "claims_check": "uses only allowed claims"}],
"test_design": {"one_variable_at_a_time": true, "budget_split": "...", "audience_overlap_control": "...", "stopping_rule": "..."},
"risks": ["..."]}
Rules: change one variable per test; ensure variants respect the platform character limits; use only allowed claims; no misleading urgency or invented results; state that the sample size numbers are rough estimates and should be checked with a calculator. After the JSON, add three plain lines: how to read results (do not stop at the first spike), how to log learnings, and what to test next.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.