Tear down competitor ads to find positioning gaps you can own
When planning a paid campaign, reviewing what competitors are already saying prevents you from blending in. This prompt systematically dissects competitor ad copy to surface the claims nobody is making — which is where you should compete.
You are a competitive positioning analyst. I will give you a set of competitor ad copy samples. Your job is to find the white space.
1. Read all ad samples. For each ad, extract: Core promise (one phrase), Proof mechanism used (stat, testimonial, feature, etc.), Emotional trigger (fear, aspiration, urgency, trust), CTA type (trial, demo, buy, learn more).
2. Build a positioning map: list the claims that appear in 3 or more ads — these are table-stakes messages. List claims that appear in only 1 ad — these are differentiated bets.
3. Identify 2–3 angles that no competitor is claiming at all. These are the positioning gaps. For each gap, write one sentence explaining why it might be unclaimed (risky to prove, niche audience, etc.).
4. For each gap, write one test headline (under 35 characters) that {{MY_BRAND}} could use to own it.
5. Flag any competitor claim that appears legally aggressive or unsubstantiated — note it as a risk if we mirror it.
Edge cases: This analysis is only as good as the sample size. Fewer than 5 ads will produce unreliable pattern detection — gather more before running this prompt.
My brand name and core offer: {{MY_BRAND}}
Competitor ad copy samples (paste all, separated by '---'): {{COMPETITOR_ADS}}
Target platform (e.g., Google Search, Meta, LinkedIn): {{AD_PLATFORM}} {{MY_BRAND}}{{COMPETITOR_ADS}}{{AD_PLATFORM}}
How to use this prompt
- Copy the prompt above (Copy button on the top-right).
- Replace each
{{VAR}}with your own value. Variables:{{MY_BRAND}}{{COMPETITOR_ADS}}{{AD_PLATFORM}}. - Paste it into one of the recommended tools below.
- Iterate: tighten constraints in the prompt if the output is generic.
Why this prompt is structured this way
The prompt is split into explicit steps because LLMs do better when the path is named, not implied. Each variable forces specificity at the input layer — vague inputs get vague outputs.
Pair this prompt with a tool
AdCreative.ai
$39/moAI-generated ad creatives scored for conversion.
AdCreative generates ad variants (static + video) and scores each one for conversion likelihood based on training data from millions of ads. Connects to Meta + Google.
Perplexity
$0/mo (Pro at $20)AI search engine with citations.
Perplexity is the answer engine Google would build if it weren't protecting search ad revenue. Cited answers, follow-up questions, focused source modes.
Claude (Anthropic)
$0/mo (Pro at $20)Frontier model with long context and strong reasoning.
Claude (Opus / Sonnet / Haiku tiers) is the assistant favored by writers and engineers who care about reasoning quality and tone. 1M token context on Opus.
ChatGPT (OpenAI)
$0/mo (Plus at $20)The category-defining general-purpose AI assistant.
ChatGPT has the broadest feature surface: image gen, voice, custom GPTs, web browsing, code execution. Often the right default; sometimes beaten on specific tasks by Claude or Perplexity.
The PlaybookPrompts weekly
One short email per week. The five sharpest prompts we found, one tool worth your attention, one anti-pattern to avoid. Unsubscribe in one click.
Newsletter signup is not configured. Set PUBLIC_NEWSLETTER_USERNAME in the build env.