Ads

Find the ad angles competitors keep repeating

Turn repeated competitor ad creatives into angles, claims, hooks, offers, and test ideas.

Best use case

Use this prompt when the source set matches the job

Use this when you have ad copy, creative descriptions, landing page URLs, or notes from a public ad library.

Before you paste

Give the prompt sources, tools, dates, and a decision

  • Paste raw notes with labels like homepage, pricing page, ad copy, SERP notes, offer page, export, screenshot, or review set.
  • Add the date you checked anything that can change, especially ads, prices, search results, AI answers, and website pages.
  • Tell AI which tools it can use: web search, deep research, files, code, browser, MCP, Semrush, Ahrefs, Similarweb, Panoramata, Sheets, or your own workspace.
  • Tell AI what decision the answer should support, so it gives you a useful recommendation instead of a generic summary.

Modern AI workflow

Use the prompt with current AI tools, not only a blank chat box

  • Use deep research or web search for current public evidence, then cite the URLs and date checked.
  • Use file or data analysis for exports, screenshots, CSVs, and historical logs. Do not summarize rows by instinct.
  • Use MCP/connectors when available so the AI can query Semrush, Ahrefs, Similarweb, Panoramata, Sheets, CRM, or your own files directly.
  • Use agent mode for multi-step research: collect, extract, compare, verify, then write.
  • Use artifacts, Canvas, tables, or charts when the output is a map, report, dashboard, or campaign plan.

Prompt

Find the ad angles competitors keep repeating

You are helping me analyze competitor ads.

My company: {{my_company}}
Competitor: {{competitor}}
Category: {{category}}
Decision I need to support: {{decision}}

Ad sources:
{{sources}}

Important rule: repeated creative patterns matter more than one clever ad.

Analyze:
1. Hooks the competitor repeats.
2. Problems, desires, objections, and proof used in the ads.
3. Offer mechanics, such as discount, bundle, quiz, consultation, trial, demo, or guarantee.
4. Creative formats that appear more than once.
5. Likely audience segment for each angle.
6. What I should test without copying the ad.

Label every conclusion as shown in the sources, a reasonable guess, or needs checking.
Return a clear table first. Then give the strongest 3 insights, the risks, the verification notes, and the recommended next moves.

- Collect or inspect the ad examples first. Group repeated hooks, claims, creative formats, offers, and landing-page follow-through before suggesting tests.
- Use any provided URLs, files, screenshots, exports, or connected tool outputs before analyzing.
- Cite the source, export, tool, or URL behind any claim that affects the decision.
Open in ChatGPT Open in Claude Open in Gemini

Edit the prompt first if needed. ChatGPT and Claude open prefilled; Gemini opens with the prompt copied.

Variables

Replace these fields before you run the prompt

Variable What it means Example
{{my_company}} Required My company The company, product, store, or service you are comparing against the competitor. A DTC skincare brand selling refillable face wash
{{competitor}} Required Competitor The competitor you want to analyze. Use one competitor at a time when the source set is deep. Brand X
{{category}} Required Market or category The buying context. This helps the AI avoid comparing the wrong kind of business. Premium skincare, France and UK
{{sources}} Required Sources and retrieval targets Paste collected sources, exports, screenshots, notes, URLs to check, or the MCP/tool datasets the AI should use. Homepage copy, pricing page, top 5 ads, title tags, Semrush export, Ahrefs export, Similarweb notes, Panoramata campaign examples
{{decision}} Required Decision to support The action you need to take after the analysis. Rewrite our landing page hero and offer comparison table

Example

Use this example to match the right level of detail

Source notes you paste into AI

My company: B2B analytics tool
Competitor: fictional tool called MetricDock
Category: ecommerce analytics
Sources: 8 ad headlines, 4 primary texts, 2 landing page notes
Decision: plan next month's ad angle tests

What a useful answer should look like

Fictional example output

Repeated pattern: MetricDock keeps using "find wasted spend" instead of "better dashboards."

Shown in the sources:
- 5 of 8 headlines mention wasted spend or missed margin.
- 3 landing pages open with audit language.

Likely:
- They are targeting operators who already have reporting but do not trust it.

Test:
- Angle A: "Your ROAS is fine. Your margin report is not."
- Angle B: "Find the products ads are quietly making unprofitable."

Verification

Check whether the answer is useful

  • The output prioritizes repeated ads over one-off ads.
  • Angles are separated from exact copy.
  • Landing page follow-through is checked.
  • Each test idea says what evidence inspired it.
  • Current claims include URLs, dates checked, and source confidence.
  • Tool outputs, exports, and AI-generated inferences are clearly separated.
  • The answer uses tables, charts, artifacts, or a report structure when that makes the decision easier.

Mistakes

Mistakes that make this prompt weak

  • Treating active ads as automatically profitable.
  • Ignoring landing pages after analyzing the ad creative.
  • Turning competitor hooks into copy-paste versions.
  • Using the prompt like a chat-only summary when modern AI could search, analyze files, run tools, or schedule follow-ups.
  • Letting the AI create a polished answer without showing the evidence trail.

Source notes

Use AI to collect data, then make it show the evidence

A good AI workflow can search, inspect pages, analyze exports, call MCP tools, compare screenshots, and build tables. Make it show URLs, dates, exports, screenshots, or connector results behind the answer before you trust the recommendation.

What you should do next

Run it once, then verify the useful parts

Replace the fields, paste a labeled source set, run the prompt, and check the answer before using it in a strategy report.

Use next