As of 13 August 2026, AI can only partly find customer demographics for your UK business.

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 order, CRM and survey systems and export a de-identified table containing only the fields needed for the analysis, such as postcode district, order date, product, value, channel and repeat-purchase status.
   2. Write down your products, price range, UK locations served, sales channels and the marketing decision the demographic analysis needs to support.
   3. Paste the business description and the de-identified data into the prompt, and state which fields are observed rather than inferred.
   4. Ask the chatbot to separate observed facts, calculated results, hypotheses and missing evidence, then save its demographic table and data-quality notes.
   5. Open the underlying customer records and compare each calculated segment with the original rows, checking that counts, percentages and location groupings have not been changed or invented.
   6. Check the proposed UK public sources directly, and compare relevant findings with official or credible published evidence rather than accepting a citation from the chatbot.
   7. Test the strongest hypothesis with a small survey, customer interview or controlled campaign, then update your customer profile only when the new evidence supports it.

   Prompt

   Act as a UK market-research analyst. Help me identify likely customer demographics for this business, but do not present guesses as facts and do not invent figures.
   
   Business:
   - Business name: [business name]
   - What we sell: [products or services]
   - Price range: [price range]
   - Location and areas served: [UK regions, towns or online]
   - Sales channels: [website, shop, marketplace, other]
   - Main business goal: [goal]
   
   Data I can provide:
   - Customer or order data: [paste a de-identified table or describe the columns]
   - Customer survey responses: [paste de-identified responses]
   - Existing customer groups: [paste any known segments]
   - Public sources already found: [paste links or extracts]
   
   Analyse only the information supplied and clearly label each statement as one of: observed fact, calculated result, reasonable hypothesis, or missing evidence. Identify the demographic variables that can actually be supported, such as age band, location, household type or income proxy, and explain the limitations of each. Do not infer sensitive characteristics or identify individuals. Do not claim to know a customer's age, ethnicity, health, religion, sexuality or other sensitive information unless it was lawfully collected, directly supplied and relevant to the analysis.
   
   Return:
   1. A table of supported customer demographics, with the evidence and sample limitations for each.
   2. A separate table of hypotheses that need testing.
   3. Any data-quality problems, including missing fields, duplicates, sampling bias and postcode or location limitations.
   4. Three practical customer-research questions or tests to validate the hypotheses.
   5. Marketing actions that are safe to try without treating the hypotheses as established facts.
   6. A short list of UK public sources I should check, with the exact claim each source could support.
   
   Do not use demographic stereotypes, estimate missing figures, or recommend excluding people from essential services. Ask concise clarification questions only if the data is too incomplete to produce a useful first analysis.

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