As of 13 August 2026, AI can only partly analyse your competitors' customer reviews.

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, chat-fluent skill, and roughly 1 hour until you can act on the result.

   How to actually do it

   1. Open the review pages or review exports for each competitor and collect the review text, rating, date, source and a stable row number without bypassing access controls or breaching the site's terms.
   2. Remove duplicate entries, promotional material and reviews that are not about the relevant product, while keeping a copy of the original data so your changes can be checked.
   3. Put the cleaned reviews into a spreadsheet with one row per review and columns for competitor, source, date, rating, review identifier and full review text.
   4. Paste the spreadsheet data, your product description and the business decision into the prompt, and ask the chatbot to analyse only the supplied reviews.
   5. Check each reported theme by locating the cited review rows and confirming that the quotations and competitor labels are accurate.
   6. Compare the analysis with your own knowledge of customer complaints, support records and product priorities, then turn only the supported findings into a competitor-analysis brief.

   Prompt

   Analyse the competitor customer reviews in the data below. The data may contain reviews for several competitors and may include a rating, date, source, competitor name and review text.
   
   Competitors: [LIST COMPETITOR NAMES]
   Our product or service: [DESCRIBE YOUR PRODUCT OR SERVICE]
   Business question: [STATE THE DECISION THIS ANALYSIS SHOULD INFORM]
   Review data:
   [PASTE REVIEW DATA OR A TABLE]
   
   Produce:
   1. A short method note stating what data was analysed, what was missing and what conclusions cannot safely be drawn.
   2. A table of recurring positive themes and negative themes for each competitor, with the number of supplied reviews mentioning each theme only if you can count them reliably.
   3. For every important theme, quote or cite several short source excerpts using the supplied review identifier, source or row number. Do not invent quotations.
   4. A cross-competitor comparison showing shared complaints, distinctive strengths and gaps that appear relevant to our product.
   5. Separate direct evidence from your interpretation. Mark weak, ambiguous or conflicting patterns clearly.
   6. Practical product, service and messaging opportunities, ranked by likely customer importance and confidence in the evidence.
   7. A list of claims that need manual checking before being used in a business decision.
   
   Do not claim that the data represents all customers. Do not infer demographics, motives or competitor facts that are not in the supplied data. Do not remove inconvenient reviews. Use plain British English.

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