Discount offers go out on ad-hoc lists, with no margin floor written down and no record of which products qualify. In this case, the immediate task is to define relevant personalized offers within stated limits. The workflow should produce personalized message variants and targeting rules, with eligibility checked against the merchant's own customer 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 relevant personalized offers within stated limits.
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 approved offer rules, the covered products with their cost basis and currency, the merchant's stated margin floor, the customer signals available in the records, and one review window of orders to test eligibility]. Match each offer to a segment the records support, state its conditions and expiry, and compute the margin the offer leaves per product against the stated floor in the merchant's own currency, holding back any offer that breaches it.
Return personalized message variants and targeting rules 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 approved offer rules, the products each offer covers with their cost basis and currency, the merchant's stated margin floor, the customer signals available in the records, and one merchant-defined window of orders to test eligibility against.
Match each offer to a segment the records support, state its conditions and expiry, and compute the margin the offer leaves per product against the stated floor in the merchant's own currency, holding back any offer that breaches it.
Deliver the message variants with their targeting rules, eligibility checks and expiry dates, verify each eligible customer against the supplied customer and product records, and list the offers held back with the margin or rule that stopped them.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
The margin each offer leaves is computed per product from the merchant's cost basis in the store currency and compared with the stated floor, because a percentage that looks safe on one product clears nothing on another; an offer below the floor is held back with the figure recorded rather than sent and explained later.
No, a segment with no supported need or no margin room receives nothing, since a generic discount trains customers to wait for the next one and spends margin the merchant never approved; the targeting rules name which segments are excluded and why, so the silence is deliberate.
An offer without a stated end runs past its intent and collides with later pricing, and a customer quoting it months later has to be refused; the expiry travels with the offer in the specification, and anyone asking after it is pointed to what is currently approved.
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.