Verification

Check AI competitor research before you trust it

Audit an AI competitor research output for unsupported claims, missing sources, and risky recommendations.

Best use case

Use this prompt when the source set matches the job

Use this after any AI competitor analysis, before sending it to a client or team.

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

Check AI competitor research before you trust it

You are reviewing AI competitor research.

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

Original sources:
{{sources}}

AI output to verify:
{{ai_output}}

Audit the output:
1. List claims that are directly supported by the sources.
2. List claims that are plausible but not proven.
3. List claims that are unsupported or risky.
4. Find missing source types.
5. Find recommendations that do not follow from the evidence.
6. Rewrite the summary with plain trust labels.

Use three labels only: shown in the sources, reasonable guess, needs checking.

- Audit the original output against the source set only. Downgrade or rewrite anything that is not supported.
- 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
{{ai_output}} Required AI output Paste the analysis you want to verify. The AI competitor analysis draft

Example

Use this example to match the right level of detail

Source notes you paste into AI

Sources: fictional pricing page notes and homepage copy
AI output: "Competitor X is winning because they are cheaper and have better onboarding."
Decision: prepare client report

What a useful answer should look like

Fictional example output

Needs checking:
- "Winning" is not supported by the provided sources.
- "Cheaper" is only supported if prices are comparable and plan limits match.
- "Better onboarding" is unsupported unless onboarding proof is in the sources.

Safer rewrite:
The sources show Competitor X makes onboarding more visible on the website. Pricing may look lower, but plan limits need verification before we call it cheaper.

Verification

Check whether the answer is useful

  • The audit uses the labels shown in the sources, reasonable guess, and needs checking.
  • Unsupported claims are rewritten, not only criticized.
  • The output lists what sources to collect next.
  • Recommendations that overreach are downgraded.
  • 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

  • Using the same AI output as its own proof.
  • Adding trust labels but not changing the recommendation.
  • Forgetting to verify screenshots, dates, and page changes.
  • 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