Two dashboards report different checkout completion rates because each one counts starts and completed orders differently. In this case, the immediate task is to measure checkout completion using a consistent definition. The output should be one written definition applied across devices and regions, with the counts reconciled.
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 measure checkout completion using a consistent definition.
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 written definitions of checkout start and completed order, start counts and completed orders for one reporting window, device, region and currency on each row, and the merchant's stated minimum session threshold]. Compute the completion rate as completed orders divided by checkout starts with that single definition applied to every device and region, report any breakdown whose start count sits below the merchant's stated minimum session threshold as raw counts instead of a rate, and flag orders whose currency conversion moves them outside the window.
Return a checkout drop-off report and prioritized remediation tests with the counts 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.
Write down, before any count is pulled, what counts as a checkout start, what counts as a completed order and whether cancelled or refunded orders are removed, then pull start counts and completed orders for one reporting window with device, region and currency recorded on every row.
Compute the completion rate as completed orders divided by checkout starts with that single definition applied to every device and region, report any breakdown whose start count sits below the merchant's stated minimum session threshold as raw counts instead of a rate, and flag orders whose currency conversion moves them outside the window.
Publish the written definition beside the rate, reconcile the sum of the device and region breakdowns against the period total and against the count of completed orders in the order export, and state which cancelled or refused orders were removed.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Only on the event the merchant named in advance, such as the first recorded checkout step, and never on a cart view. The rule must stay fixed across every reporting window, because switching start definitions between periods produces a difference that looks like a performance change but is only a counting change.
Choose one treatment and document it, since removing them changes what the rate measures. Whatever is chosen has to be applied identically to every period compared, otherwise the trend mixes two definitions rather than showing the real movement of the funnel.
Almost always in the denominator, because one counts cart views and the other counts the first checkout step. Before deciding which number is right, write both start definitions side by side and rebuild each rate on one shared definition, then check the totals against the order export.
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.