The merchant is comparing an ad-platform cost per purchase against a lifetime value covering a different set of customers. In this case, the immediate task is to compare CAC with a compatible customer-value measure. The workflow should produce a CAC calculation and segment comparison, restating either side where the records show a different scope or window.
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 compare CAC with a compatible customer-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: [acquisition spend for the reporting window, the count of customers meeting the stated new-customer definition, the platform-reported cost-per-purchase figure, the customer-value measure supplied for comparison, and the scope, window, currency and revenue basis recorded for each]. Restate both sides onto one common scope, window, currency and revenue basis before comparing, dividing the agreed acquisition spend only by customers meeting the stated new-customer definition, and where a side cannot be restated, report it separately with its original basis named instead of forcing it into the ratio.
Return the CAC calculation and a segment comparison with both sides reconciled 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.
Gather, for one stated reporting window, the acquisition spend the merchant treats as acquisition cost, the count of customers meeting the merchant's stated new-customer definition, the platform-reported cost-per-purchase figure and the customer-value measure supplied for comparison, recording for each the customer scope, time window, currency and revenue basis it was built on.
Restate both sides onto one common scope, window, currency and revenue basis before comparing, dividing the agreed acquisition spend only by customers meeting the stated new-customer definition, and where a side cannot be restated, report it separately with its original basis named instead of forcing it into the ratio.
Deliver the CAC calculation with a segment comparison showing each side before and after restatement, reconcile the new-customer count against the order export and the spend total against the ad-platform billing record, and note every figure kept on its original basis.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Restate both onto one scope before dividing, usually the merchant's stated new-customer definition, because a value measure covering all customers set against a cost covering only newly acquired ones overstates the return; where a side cannot be restated, keep it out of the ratio and label it with its own basis.
Neither automatically: move both to the merchant's stated reporting window, and if either source cannot be rebuilt for that window, present the pair side by side with the mismatch named rather than dropping the customer records that fall outside it.
Reconcile the new-customer count with the order export, the spend total with the ad-platform billing record and the value total with the sales records for the same window; any gap is listed with its likely source, such as attribution settings, currency conversion or a window cutting across a campaign, before the figures are published.
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.