As of 13 August 2026, AI can only partly analyse local demand by UK postcode.

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. Define the decision you need to make, the product or service, the demand measure, the date range and the UK postcode geography you want compared.
   2. Open the source files and export the relevant postcode-level records, such as sales, enquiries, visits or campaign results, with dates and the fields needed to group them by area.
   3. Gather supporting source links or files for any context you want to use, such as population, competitor locations or search data, and record the date and coverage of each source.
   4. Remove unnecessary personal information, standardise postcode formatting and label each record with the postcode district or other geography you want analysed.
   5. Paste the prompt into a chatbot and attach the cleaned data and source notes, then answer its clarification questions before asking it to produce the ranked table and findings.
   6. Check every total, percentage and ranking against the source files, open each cited link, and compare the recommendations with your current campaign budget, service area and operational capacity before acting.

   Prompt

   Analyse local demand for [product or service] across these UK postcodes: [list of postcodes or postcode districts]. Use only the files and source links I provide. Treat demand as [define the measure, such as search interest, enquiries, orders, footfall or sales].
   
   Create:
   1. A ranked table of the areas by demand.
   2. The measure used, time period, sample size and source for every result.
   3. Comparisons with population, customer density, competition or other context only where the supplied data supports them.
   4. Clear separation between observed data, calculated results and assumptions.
   5. Missing-data warnings, postcode-coverage limitations and any reasons the comparison may be misleading.
   6. Three practical marketing actions, each linked to a specific finding.
   
   Do not invent figures, fill gaps with guesses, imply that correlation proves demand, or claim that a postcode is attractive without evidence. Show the calculation for every ranking or percentage. Ask me concise questions before analysing if the demand definition, date range, postcode geography or business objective is unclear. End with a short list of checks I must complete before using this for budget or location decisions.

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