Nobody can say which customers have genuinely left for good, yet budget is being committed as though the answer were already known. In this case, the immediate task is to identify possible churn using relevant purchase history. The workflow should produce an at-risk customer definition and winback plan stated as risk rather than as settled fact.
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 possible churn using relevant purchase history.
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: [dated order history, the stated observation window and churn definition, the expected repurchase cycle, the analysis date, and the rule for excluding newly acquired customers]. Judge each customer by comparing the gap since their last order against both the observation window and their expected cycle, assign risk only where the evidence in the records supports it and state the gap and cycle behind every judgement, and exclude customers too new to have established a pattern instead of scoring them on thin history.
Return an at-risk customer definition and winback plan 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 dated order history, the length of the merchant's stated observation window and the churn definition attached to it, the expected repurchase cycle for the products involved, the analysis date, and the rule that decides how new a customer must be to be excluded.
Judge each customer by comparing the gap since their last order against both the observation window and their expected cycle, assign risk only where the evidence in the records supports it and state the gap and cycle behind every judgement, and exclude customers too new to have established a pattern instead of scoring them on thin history.
Deliver an at-risk customer definition and a winback plan written as risk rather than as fact, listing each flagged customer with the gap, cycle and evidence behind the flag, then verify the flagged names against the order export and list separately any customer the records cannot settle either way.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
A risk judgement, and the page says so: it records that the observed gap passed the merchant's threshold, not that the customer has left, and anyone on the list may still order the following week.
Under the merchant's rule, usually excluded or flagged weakly, because a single order gives no interval to compare against; forcing a judgement on it produces risk levels that are not comparable with those of customers whose pattern is actually observed.
The last order date, the expected cycle, the observed gap and the threshold applied, so a reviewer can recalculate the flag from the records; a flag missing those fields cannot be checked and is reported as unsupported.
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.