As of 13 August 2026, AI can analyse your sales data for market trends.

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. Export the relevant sales records from your CRM, ecommerce platform or accounting system into a spreadsheet, including dates, products, quantities, revenue, discounts, costs, customers, regions and channels where available.
   2. Remove unnecessary personal data, retain the column headings, and add a note explaining currency, refunds, cancellations, tax treatment, reporting periods and any changes to prices, products or sales processes.
   3. Open an approved AI chat or Polymer and upload the spreadsheet with the business context and decision you need to inform.
   4. Paste the supplied prompt and ask the tool to produce the data-quality report before relying on any trend.
   5. Compare the reported totals, date range, refunds, missing values and calculated changes with the original spreadsheet or a pivot table made in your spreadsheet software.
   6. Separate findings supported by your sales data from claims about the wider market, then add reliable external sources for any market comparison the tool has identified as missing.
   7. Ask the tool to revise the findings using the checked figures and sources, and send the final table to a colleague who understands your products and reporting rules before making a commercial decision.

   Prompt

   Analyse the attached sales data for decision-useful trends. Treat the data as internal sales evidence, not proof of wider market conditions.
   
   First, describe the columns, date range, missing values, duplicate records, unusual values and any assumptions needed. Flag data-quality problems before drawing conclusions.
   
   Then analyse trends by time period, product or service, customer segment, region, sales channel and any other useful fields in the data. Compare revenue, units, average order value and margin only where those fields are present. Separate genuine changes from changes that may be caused by missing data, seasonality, promotions, price changes, product availability, customer mix or reporting changes.
   
   For each important finding, provide:
   - the exact fields and rows or periods supporting it
   - the direction and size of the change, calculated only from the supplied data
   - at least one plausible alternative explanation
   - the confidence level and what evidence is missing
   - the business question the finding raises
   
   Do not invent figures, market data, competitors, causes or customer motives. Do not call an internal sales pattern a market trend unless external market evidence is supplied. Clearly label anything that would require external research. Finish with a concise table of findings, evidence, limitations and recommended next checks. Show the calculations for any headline figures so I can compare them with the source data.
   
   Business context: [describe the business, products, customers, sales channels, pricing changes, promotions, stock issues and reporting rules]
   Decision this analysis will inform: [describe the decision]
   Relevant external evidence, if available: [paste sources or say none]

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