The merchant wants to look after the best customers but has no agreed measure of value, so refunds get mixed in. In this case, the immediate task is to identify high-value customers using a stated value measure. The workflow should produce a customer segment table and interpretation guide, ranking customers by that measure.
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 high-value customers using a stated value measure.
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 purchase history with stable customer identifiers, order dates, order values and refund entries for the stated span, the value measure chosen by the merchant, its currency, and the treatment applied to refunded and cancelled orders]. Apply that one measure to every customer over the same span, ranking them by the resulting value and stating whether refunds are netted out before or after ranking, then check how much of the total sits with the top-ranked accounts rather than reporting the ranking alone.
Return a customer segment table and interpretation guide with the values 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 the purchase history with stable customer identifiers, order dates, order values and refund entries for one stated span, together with the value measure the merchant has chosen, the currency it is expressed in and the treatment applied to refunded and cancelled orders.
Apply that one measure to every customer over the same span, ranking them by the resulting value and stating whether refunds are netted out before or after ranking, then check how much of the total sits with the top-ranked accounts rather than reporting the ranking alone.
Deliver a customer segment table and an interpretation guide showing rank, value, order count and last order date per customer, verify that the ranked values sum to the sales total for the span under the stated measure, and flag customers whose value rests on a single order.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
No, one measure is chosen for the whole ranking and named in the output, because a list mixing gross revenue for some customers with net margin for others cannot be ordered meaningfully; if the merchant wants both, they are produced as two separate rankings compared side by side.
Because a ranking where most of the total sits with a handful of accounts carries different risk from a broad spread of similar customers; the report states how much of the total the top group holds so decisions about service levels and retention spend rest on the shape of the list, not the order of names.
Exactly as the merchant's stated treatment directs, applied to every customer before ranking, because netting refunds for some accounts and not others changes positions without any change in behaviour; orders still in dispute at the analysis date are listed rather than silently included or dropped.
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.