Google Ads credits conversions on its own window and model, so reported results drift from the orders sitting in the store. In this case, the immediate task is to compare Google Ads attribution with store transactions. The workflow should produce a unified reporting model and discrepancy log tying every variance to supporting 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 compare Google Ads attribution with store transactions.
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: [conversion exports with click identifiers and conversion timestamps, the configured attribution window and model, and store transactions with refund and cancellation status for a window that includes late conversions].
Compare each attributed conversion with its transaction on identifier and amount, separating differences caused by conversion delay, by click-based credit the store cannot observe and by later refunds or cancellations, and flag any identifier appearing more than once in the same window as a suspected duplicate.
Return a unified reporting model and discrepancy log with every variance tied to supporting 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 conversion exports with their click identifiers, the attribution window and model configured on the account, the conversion timestamps each row carries, and the store transactions with their refund and cancellation status for a window long enough to include late conversions.
Compare each attributed conversion with its transaction on identifier and amount, separating differences caused by conversion delay, by click-based credit the store cannot observe and by later refunds or cancellations, and flag any identifier appearing more than once in the same window as a suspected duplicate.
Deliver the unified reporting model and discrepancy log tying every variance to supporting records, then verify that the variance total equals reported conversions minus reconciled transactions, that periods are compared only after their attribution window has closed and that return and cancellation dates fall inside the same period.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Credit is assigned from the click while the order is recorded when it is placed, and conversions keep arriving after the period closes. Compare on identifiers and timestamps over a window extending past the configured attribution period before calling any number wrong.
Look for the same transaction identifier, or identical amount and timestamp pairs, appearing more than once inside the stated window. Each suspected duplicate is logged with both rows, because a genuine repeat purchase and a double count look identical until the records are opened.
After the attribution window for that period has closed and refunds or cancellations touching it have been applied. Periods still open are marked provisional and re-issued later, so a mid-window figure is never set beside a settled one.
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.