A campaign is planned for the most frequent buyers, but the current list was built from basket size rather than order count. In this case, the immediate task is to identify customers with frequent purchases. The workflow should produce a customer segment table and interpretation guide, counting separate orders inside one window in the merchant's own 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 identify customers with frequent purchases.
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: [stable customer identifiers, order ids and dates, refund and cancellation records, the stated observation window and analysis date, and the merchant's minimum order count for frequent buyers]. Count one order per distinct order id placed inside the window under the stated status and refund treatment, keep that count separate from the units in any basket so one large order stays one order, treat split shipments of a single checkout as the one order they came from, and mark a customer frequent only when the counted orders reach the merchant's stated minimum.
Return a customer segment table and interpretation guide with each membership verified against the supplied 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 stable customer identifiers, the order history with order ids and dates, refund and cancellation records, the start and end of the merchant's stated observation window together with the analysis date it is measured from, and the minimum number of separate orders a customer must reach to count as frequent.
Count one order per distinct order id placed inside the window under the stated status and refund treatment, keep that count separate from the units in any basket so one large order stays one order, treat split shipments of a single checkout as the one order they came from, and mark a customer frequent only when the counted orders reach the merchant's stated minimum.
Deliver a customer segment table and interpretation guide listing each frequent customer with their order count and a separate column for average units per order, reconcile the sum of per-customer order counts against the qualifying orders in the order export, and list every customer whose membership would change if a disputed order were counted the other way.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
No, the frequency measure counts distinct order ids, so a basket full of units is still one order; units are reported alongside as a separate column because a customer can be high in units and low in orders at the same time.
A split shipment stays the single order it originated from and an exchange enters the count only if the merchant's qualifying rule admits it, because treating each shipment as a new order would manufacture frequent buyers out of one checkout.
Follow the merchant's rule, and the page states which it used: including the first order lets anyone who returned once qualify, while excluding it measures repeat behaviour after acquisition, and the two readings give different segment sizes.
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.