Segments are being ranked against one another although some were measured over a longer window and others on a different value basis. In this case, the immediate task is to compare customer lifetime value across relevant segments. The workflow should produce an LTV analysis with transparent assumptions tied to the segment definitions actually in use.
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 customer lifetime value across relevant segments.
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: [segment definitions with their original measurement windows and value bases, per-customer order history from first order to the cut-off date, refund and cancellation records, and the merchant's minimum segment size]. Recompute every segment on one common window anchored at each customer's own first order rather than the calendar period the segment was created in, hold the value basis constant by excluding cancelled and refunded orders and stating whether shipping and tax are counted, and mark any segment below the merchant's stated minimum customer count as indicative instead of ranking it.
Return an LTV analysis with transparent assumptions 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.
Pull every segment definition currently in use together with the date range each one was measured over, the value basis behind each figure such as gross revenue or margin after refunds, and the full order history of the customers in each segment from first order to the analysis cut-off.
Recompute every segment on one common window anchored at each customer's own first order rather than the calendar period the segment was created in, hold the value basis constant by excluding cancelled and refunded orders and stating whether shipping and tax are counted, and mark any segment below the merchant's stated minimum customer count as indicative instead of ranking it.
Deliver a segment LTV comparison listing for each segment its customer count, the window and basis actually applied, and the original figure beside the recomputed one with the reason for the gap, and reconcile the sum of segment customers against the customer export before publishing.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Each customer enters the window at their own first order and is measured to the same cut-off date, so every segment gets equal time to accumulate value; customers acquired after the cut-off are excluded, and a segment whose original window cannot be reconstructed is reported as unreconciled rather than ranked.
It is listed with its customer count and its figures marked indicative, because a value per customer swings sharply on a handful of accounts and a rank would overstate the difference; it stays in the table with the flag so it is not silently dropped from the comparison.
Each gap is attributed to one of three causes: a different window, a different value basis, or a changed segment definition; where a gap survives all three, it is treated as a data problem and the figure is withheld until the customer records reconcile.
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.