The retention list mixes people who are overdue with people who were never due yet, so outreach lands on customers still ordering normally. In this case, the immediate task is to define an at-risk customer group with clear rules. The workflow should produce an at-risk customer definition and winback plan read off 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 define an at-risk customer group with clear rules.
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: [purchase history with dates, per-product repurchase cycles, the prior campaign contact log, the offer limits and contact cadence, and opt-out or suppression records]. Write the at-risk rule as a comparison of the observed gap against that customer's expected cycle, keep out everyone still inside their cycle, everyone contacted within the merchant's stated cadence and everyone holding an opt-out, apply the offer limits to what each flagged customer may be sent, and mark any customer whose cycle or contact history is incomplete as unresolved.
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 purchase history with dates, the expected repurchase cycle for the products each customer buys, the prior campaign contact log with its channels, the offer limits and contact cadence in force, and any opt-out or suppression records.
Write the at-risk rule as a comparison of the observed gap against that customer's expected cycle, keep out everyone still inside their cycle, everyone contacted within the merchant's stated cadence and everyone holding an opt-out, apply the offer limits to what each flagged customer may be sent, and mark any customer whose cycle or contact history is incomplete as unresolved.
Deliver an at-risk customer definition and a winback plan listing each name with the gap, cycle, last contact and permitted offer, then reconcile the list against the order export to confirm no flagged customer has ordered since and against the contact log to confirm nobody is approached twice.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Because their gap has not yet exceeded what those products normally take, so the flag would describe impatience rather than risk; only a gap past the expected cycle separates a delayed reorder from a normal one.
It removes them from the current send under the merchant's stated cadence, not from the at-risk definition, so the segment keeps its size while the outreach avoids contacting the same customer again inside the stated interval.
In a separate group with the missing field named, cycle or contact history, rather than placed by default, since a default placement changes the size of the send list without any new evidence.
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.