Order volume is rising, but the merchant cannot say whether that came from new buyers or existing ones ordering more. In this case, the immediate task is to analyze customer growth and purchase distribution. The workflow should produce a customer segment table and interpretation guide, reconciled against the merchant's purchase and refund records.
First replace every [bracketed] placeholder with real store scope and constraints, then add any actual records or data you have, and paste it into your preferred AI assistant or Spark agent. Spark will follow this page's workflow to produce structured output and verification steps.
Act as a Shopify operations specialist.
Help me analyze customer growth and purchase distribution.
My store context is [describe the business, products and target audience].
My scope is [specify the affected products, pages, customers or reporting period]. Use these inputs: [the order export with stable customer identifiers, order dates, order values and refund or cancellation entries for the analysis window, the analysis date, and the merchant's rule for which orders count toward the totals]. Split the growth between customers whose first order inside the window is their earliest recorded order and those with earlier orders, and report the distribution of orders and value per customer alongside the totals so a rise driven by a few heavy accounts is not read as broader acquisition.
Return a customer segment table and interpretation guide with totals reconciled against the records for the specified task.
Show the relevant evidence or before-and-after examples and explain how I can verify the result.
If essential data is missing, ask for it and mark unsupported conclusions as unknown.
Do not invent metrics, product claims or customer facts.
For any publication, message, account or store change, use only connected tools within my explicitly authorized scope and report success only after verification; otherwise provide the draft or proposed steps.Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
Collect the order export with stable customer identifiers, order dates, order values and refund or cancellation entries for one stated analysis window, together with the analysis date and the merchant's rule for which orders count toward the totals.
Split the growth between customers whose first order inside the window is their earliest recorded order and those with earlier orders, and report the distribution of orders and value per customer alongside the totals so a rise driven by a few heavy accounts is not read as broader acquisition.
Deliver a customer segment table and an interpretation guide, reconcile the order count and value totals against the order export, and list every order that could not be attributed to a customer as an unresolved input.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Each customer is placed by comparing their first order inside the window with their earliest recorded order anywhere in the history, and the difference is then explained with order counts and value per customer, because a rise concentrated in a few existing accounts calls for a different response from broad new-customer growth.
The same rise in value can come from many customers ordering once or a handful ordering repeatedly, and the spread of orders per customer shows which; the report therefore gives both the totals and the per-customer spread so the follow-up matches the actual shape of the growth.
They are excluded from segment counts and reported as a separate unresolved line, because guessing an identity would move customers between groups; if the unresolved share is large enough to change the reading, the report says so instead of presenting the split as complete.
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
Ciwi Spark builds Shopify-native AI tools and agents around the workflows merchants actually run: research, ads, translation, and customer support. Stop rewriting the same prompts by hand.