As of 13 August 2026, AI can analyse your competitors' SEO keywords.

What to actually do

1. Hand it to a person

   The route this page recommends

   A person who owns the outcome does this end to end, worth it when the failure is dear.

2. Use a tool built for this

   Second choice

3. Do it yourself

   The distant third

   A chat interface, power-user skill, and roughly 1 hour until you can act on the result.

   How to actually do it

   1. Open your SEO platform or keyword research tool and export the competitor keyword data as a CSV or spreadsheet, including the keyword, competitor URL or domain, ranking position, estimated volume, difficulty and any intent fields available.
   2. Choose several genuinely comparable UK competitors and remove domains that target a different country, audience or business model.
   3. Write down your website, products or services, target customers, geographic area, commercial goal and topics you will not target.
   4. Paste the business details, the unedited export and the copyable prompt into a chatbot, keeping the column headings and source names intact.
   5. Ask the chatbot to separate direct observations from inferences and to identify missing fields instead of filling them in.
   6. Open the current UK search results for the highest-priority opportunities and compare the ranking pages, search intent and competitor coverage with the drafted analysis before creating or changing pages.
   7. Put accepted opportunities into your content plan, recording the source export date and the page you intend to create so the analysis can be repeated when the data changes.

   Prompt

   Analyse the competitor SEO keyword data below for my UK business.
   
   My business:
   - Website: [YOUR WEBSITE]
   - Products or services: [DESCRIBE THEM]
   - Target customers: [DESCRIBE THEM]
   - Geographic target: [UK, or specific UK locations]
   - Main commercial goal: [LEADS, SALES, BOOKINGS, SIGN-UPS OR OTHER]
   - Topics or services I do not want to target: [LIST THEM OR WRITE NONE]
   
   Competitor data:
   [PASTE CSV OR TABLES HERE]
   
   For each row, use the supplied figures and labels exactly. Do not invent keywords, search volumes, rankings, traffic, difficulty scores, intent or competitor coverage. If a field is missing, say that it is missing. Treat third-party volume, difficulty, traffic and ranking figures as estimates, not facts.
   
   Produce:
   1. A short summary of the main patterns.
   2. A table of keyword clusters, including the cluster name, representative keywords, competitors ranking for them, apparent search intent, business relevance, and evidence from the supplied data.
   3. Gaps where competitors have visible coverage and my website appears not to, separating clear gaps from possible gaps.
   4. Duplicate or overlapping keywords that should be handled by one page rather than several.
   5. A prioritised list of up to 20 opportunities, scored as high, medium or low priority. Explain each score using commercial relevance, competitor coverage, apparent intent and the supplied difficulty or volume data. Do not create a numerical score unless the data already contains one.
   6. A suggested page type for each priority opportunity, such as service page, product page, category page, comparison page or informational article.
   7. A list of claims that need checking against current UK search results before publication.
   8. Three practical next actions.
   
   Keep the recommendations specific to my business. Distinguish observed data from inference. Do not recommend targeting a keyword solely because it has a high estimated volume.

   Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.