As of 13 August 2026, AI can analyse seasonal trends in your 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, chat-fluent skill, and roughly 30 minutes until you can act on the result.

   How to actually do it

   1. Open your sales or operational spreadsheet and make sure each row has a real date, a measurable value such as sales or orders, and any useful fields such as product, channel, region, promotion, price or stock status.
   2. Add a separate note listing known promotions, price changes, stock-outs, closures, exceptional orders and other events that could affect the figures.
   3. Remove unnecessary personal data, correct obvious date and number formatting problems, and save a copy of the original file before sharing the working copy.
   4. Open Julius AI or another approved chatbot, upload the working copy and paste the prompt with your business context and event note filled in.
   5. Ask the tool to rerun the analysis if it groups dates inconsistently, omits a category, uses unexplained estimates or presents a conclusion without showing the source periods and figures.
   6. Compare every reported total and chart against the original spreadsheet using the same date filters, then mark each pattern as supported, uncertain or explained by a known event.
   7. Share the checked findings with the colleague responsible for stock, staffing or finance and agree which hypothesis to test before changing the business plan.

   Prompt

   Analyse the attached business dataset for seasonal trends. Use only the data provided and do not invent missing values, explanations or events. First describe the columns, date range, missing values, duplicate rows and any obvious data-quality problems. Then calculate and show the relevant totals and comparisons by month or other appropriate period, using consistent periods throughout. Identify recurring patterns, state how much data supports each pattern, and separate genuine evidence from possible explanations. Check whether promotions, price changes, stock-outs, closures, channel mix or unusual events could explain the apparent patterns. Produce clear tables and charts where useful. For every important conclusion, cite the exact columns, periods and figures used. Do not claim causation from correlation. If the data is insufficient to establish seasonality, say so and list the specific additional data needed. End with: (1) findings that are safe to use as working hypotheses, (2) findings that need further checking, and (3) practical questions I should answer before making a business decision. Business context: [describe your business, products or services, sales channels and the decisions you want this analysis to support]. Known events, promotions, price changes, stock-outs or closures: [list them, or write none known].

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