Website analysis
Find what a competitor website is really selling
Analyze a competitor website by page structure, proof, offers, friction, and message clarity.
Best use case
Use this prompt when the source set matches the job
Use this after you collect the homepage, pricing page, product page, and one conversion page from a competitor.
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 what a competitor website is really selling
You are helping me analyze a competitor website.
My company: {{my_company}}
Competitor: {{competitor}}
Category: {{category}}
Decision I need to support: {{decision}}
Sources I collected:
{{sources}}
Do not invent facts. If a source is missing, say what is missing.
Analyze:
1. What the competitor wants visitors to understand first.
2. The main offer, proof, objections handled, and objections ignored.
3. The page structure and conversion path.
4. The strongest messaging patterns.
5. The weak spots or unclear claims.
6. What I should learn, ignore, and test.
Return a clear table first. Then give the strongest 3 insights, the risks, the verification notes, and the recommended next moves.
- Open or inspect the provided website pages first. Compare current copy, section order, proof, CTAs, and friction before giving recommendations.
- 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. 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: refillable skincare brand
Competitor: fictional brand called ClearForm
Category: premium skincare
Sources: homepage hero, product page sections, pricing block, FAQ copy
Decision: decide what to rewrite on our product page What a useful answer should look like
Fictional example output
ClearForm leads with sensitive-skin reassurance, not sustainability.
Strong spots:
- The product page explains who should use the product before listing ingredients.
- The FAQ handles irritation, returns, and refill timing.
- The pricing block makes subscription savings easy to compare.
Weak spots:
- Sustainability proof is thin.
- Before/after claims need source verification.
- The final CTA repeats the same line instead of answering a new objection.
Next move: test a product page order that starts with skin concern, then product mechanism, then refill proof. Verification
Check whether the answer is useful
- The analysis separates facts from interpretation.
- Every recommendation points back to a page section or source note.
- Weaknesses are framed as test ideas, not absolute truth.
- Missing pages or unclear evidence are listed.
- 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
- Pasting only a homepage and asking for a full strategy.
- Asking the AI to rank the competitor without proof.
- Copying the competitor's structure before checking your own offer.
- 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.