A store mixes consumables replenished on a schedule with durable goods bought rarely, so one threshold misreads the base. In this case, the immediate task is to identify inactive customers relative to normal buying cycles. The workflow should produce a customer segment table and interpretation guide keyed to each last-order date and its product cycle.
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 inactive customers relative to normal buying cycles.
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: [each customer's last order date, the products bought with their stated repurchase cycles, the analysis date, and the merchant's rule for products with no stable cycle]. Measure each customer's gap as the days from their last order to the analysis date, compare it against the repurchase cycle of the products they actually bought rather than one store-wide number, hold out every customer whose gap is shorter than that cycle because they are not yet due to reorder, and place customers with an unknown cycle in a separate group instead of giving them a default.
Return a customer segment table and interpretation guide 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 each customer's last order date, the products or categories they bought with the repurchase cycle the merchant states for each, the analysis date the gap is measured to, and the rule that governs customers whose products have no stable cycle.
Measure each customer's gap as the days from their last order to the analysis date, compare it against the repurchase cycle of the products they actually bought rather than one store-wide number, hold out every customer whose gap is shorter than that cycle because they are not yet due to reorder, and place customers with an unknown cycle in a separate group instead of giving them a default.
Deliver a customer segment table and interpretation guide giving each inactive customer's last order date, cycle and gap, verify every gap against the order export so no later order is missed, and report the unknown-cycle group separately with what would be needed to place it.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
The rule the merchant states, and the page names it: the shortest cycle reads the customer as overdue early, the longest waits for the durable item, and one rule is applied to every mixed basket so membership is not decided case by case.
No, they are excluded before any comparison happens, because a gap shorter than the expected cycle means the customer is simply between purchases; only a gap longer than the cycle is evidence of a delayed reorder.
Those customers go into an unknown-cycle group reported separately instead of being given a guessed interval, since a default placement would move the inactive count without any new order being observed.
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.