Turn Raw Sales Data Into Actionable Insight
Most small sellers look at their data but never actually read it. The numbers just sit there, no action comes out. This prompt takes the raw sales data you already have and turns it into a concrete priority in three steps: what is happening, why it is happening, what you should do about it.
You are an experienced ecommerce data analyst. Your goal is to pull concrete, actionable insights out of the sales data I give you. Never invent a number, percentage, or trend. Only write observations that can actually be derived from the data I provide. If the data is not enough to draw a conclusion, say "this result needs the following additional data." Use the following information for your analysis: [Platform]: (Shopify, WooCommerce, Amazon, Etsy, etc.) [Analysis Period]: [Sales Data]: (paste as product, quantity, revenue) [The Question or Problem Triggering This Analysis]: Structure the analysis under these headings: 1. **Standout Patterns**: the 3 most notable observations in the data. 2. **Top and Bottom Performers**: by product, based strictly on the numbers you gave. 3. **Likely Causes**: hypotheses that could explain the observed pattern (not a certain claim). 4. **Recommended Actions**: concrete next steps split into Quick (this week) and Medium-Term (this month). 5. **Missing Data Warning**: what additional data you would need for a more reliable conclusion.
How to use it
- Use it when reviewing your end-of-month sales report, to understand what the numbers actually mean beyond the totals.
- Use it to form your first hypotheses before you start digging into why a product sold less than expected.
- Use it to see which products are genuinely standing out before you make a restock or purchasing decision.
Example / tip
A home textiles seller pastes the last 3 months of Shopify sales data. The output points out that two products consistently sell together, flags one product with high views but low sales as a sign of a possible price or image problem, and recommends an A/B test for that listing.
Usage example
Copy the prompt as is, fill in the bracketed fields for your own business, and paste it into ChatGPT or Claude. The more concrete your input, the more useful the output. Take the first draft, ask for a one-sentence fix on whatever you don't like, then give it a final pass in your own voice.
When not to use it
Don't force it if you have no real input to work with. A prompt doesn't fill an empty field with data, it organizes and speeds up what you already know. Never publish the output unchecked; AI sometimes produces a claim that sounds right but is wrong or made up. Always verify anything that needs proof yourself: numbers, prices, guarantees.
Output quality checklist
- Is the output specific to your input, or generic filler that fits any business? If it's generic, run it again with more concrete input.
- Does every number, ratio, or claim have something backing it? Delete the unbacked ones or soften them honestly.
- Does it sound like you? Simplify the cliches and inflated lines in your own voice.
- Does it give one clear next step? If the reader knows what to do, the output did its job.
