Two spreadsheets quote different customer values because one folds forecast revenue into the total and the other never subtracts refunds. In this case, the immediate task is to calculate observed customer value and separate projections. The workflow should produce an LTV analysis reconciled against completed orders 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 observed customer value and separate projections.
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: [customer order history with dates and values, the chosen revenue or margin basis, the refund, tax and shipping treatment, the currency and reporting window, and the inputs permitted for any projection]. Compute observed value first as the net of completed orders inside the window under the stated basis, currency and refund treatment, then build any projection as a separate figure from the merchant's stated method and horizon with each assumption written next to it, never folding the two into one number.
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.
Collect customer order history with dates and values, the value basis the merchant has chosen between revenue and margin, the treatment for refunds, cancellations, taxes and shipping, the currency and reporting window, and the inputs any projection is allowed to use.
Compute observed value first as the net of completed orders inside the window under the stated basis, currency and refund treatment, then build any projection as a separate figure from the merchant's stated method and horizon with each assumption written next to it, never folding the two into one number.
Deliver an LTV analysis showing observed value, projected value and assumptions in separate columns, reconcile the observed totals against the order export line by line, and mark customers whose history is too short for the stated method as observed only.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Because the observed part is measured from orders and the projected part rests on assumptions; publishing one number hides that split and makes two periods incomparable as soon as the assumption behind the projection changes.
Completed orders inside the reporting window under the merchant's stated status and refund treatment, net of refunds where the rule says so, with pending, cancelled and out-of-window orders excluded and the exclusions listed so the total can be reproduced.
When the customer's history is too short for the merchant's stated method, in which case the page reports observed value only rather than extending a thin pattern into a number that looks as firm as the measured part.
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.