Ad spend is known, but it is divided by every order in the period rather than by the customers actually acquired. In this case, the immediate task is to calculate customer acquisition cost for eligible new customers. The workflow should produce a CAC calculation and segment comparison, listing exclusions and grounding the count in the merchant's 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 calculate customer acquisition cost for eligible new customers.
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 cost items defined as acquisition spend with their window and currency, the customer and order records showing each customer's first order date, the stated definition of a newly acquired customer, the exclusion rules for test, refunded and cancelled first orders, and the segment definitions]. Count only the customers meeting that definition inside the window, applying the stated rule for refunded or cancelled first orders consistently, then divide the agreed costs for the same window and currency by that count and list every exclusion with its volume so the figure can be rebuilt.
Return the CAC calculation with a segment comparison and every input verified 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.
Collect the cost items the merchant defines as acquisition spend with the window and currency each covers, the customer and order records with the identifiers that show when each customer first ordered, the stated definition of a newly acquired customer, the exclusions such as test orders and the rule for refunded or cancelled first orders, and the segment definitions.
Count only the customers meeting that definition inside the window, applying the stated rule for refunded or cancelled first orders consistently, then divide the agreed costs for the same window and currency by that count and list every exclusion with its volume so the figure can be rebuilt.
Deliver the CAC calculation and a segment comparison showing the cost, the customer count and the resulting figure per segment, then reconcile the customer count with the merchant's customer records and the cost total with the recorded spend for the window, and mark any segment below the merchant's stated minimum customer count as indicative only.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
The merchant states the definition, usually a customer whose first order falls inside the window and who has no earlier order, and it is applied unchanged to every segment. The definition is recorded beside the figure because changing it changes the denominator; a customer identified only by an email that later reorders is counted once, at the first order.
They follow the eligibility rule the merchant sets, and that rule is applied to the baseline and to the current period alike. Including a refunded first order lowers the figure while removing it raises the figure, so the choice is stated in the output; orders still in dispute are listed separately rather than being silently kept or dropped.
The segments the merchant already compares, such as channel or campaign, each reported with its own cost, customer count and resulting figure. One blended figure hides an expensive channel behind a cheap one; any segment below the merchant's stated minimum customer count is labelled indicative, because a small count swings the result.
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.