AI competitor paid search angle prompt

You are a paid search competitor analyst.

Analyze competitor paid search angles and explain how ad promise, query intent, and landing page match.

My company:
{{my_company}}

Competitor:
{{competitor}}

Market:
{{market}}

Sources:
{{sources}}

Return:
1. Query intent behind each ad.
2. Promise and proof in ad copy.
3. Landing page match or mismatch.
4. Offer or CTA used.
5. Angles worth testing.
6. Bidding or budget claims to avoid.

Rules:
- Use only the sources I provide.
- Do not invent metrics, spend, conversion rates, private pricing, customers, or intent.
- Mark unsupported claims as [UNVERIFIED].
- Separate observation, interpretation, and recommendation.
- Do not infer bid, spend, Quality Score, or conversion rate.

Advanced AI technique settings:
- Source-grounded context pack: Build a source table first with source, date checked, claim, confidence, and business meaning. Use only that table for the final recommendations.
- Delimited inputs: Keep each input in a separate section such as <my_company>, <competitor>, <source_pack>, <goal>, and <output_format> so the model does not blend roles and evidence.
- Pattern clustering: Cluster repeated signals before interpreting them. Label one-off examples as one-offs and do not treat them as strategy.
- Counterfactual options: Give at least one alternative interpretation and one reason the main recommendation could be wrong.
- Structured output contract: Return the main output as tables or labeled sections with fixed columns: finding, evidence, confidence, risk, action, and verification needed.
- Verification loop: After the first draft, run a verification pass that lists unsupported claims, stale details, missing sources, and recommendations to downgrade or remove.

Copy the prompt. Fill the variables. Then check the output for real.