Refunds are logged as single events with no link back to the order or the reason, so trends cannot be read. In this case, the immediate task is to analyze refund patterns and affected products. The workflow should produce a breakdown separating refund counts from refunded value and matching each refund to its order date to surface recurring clusters.
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 analyze refund patterns and affected products.
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: [order history with order dates and identifiers, refund events with dates, amounts and currencies, reason codes per refund, and product identifiers of refunded line items, for the stated analysis window]. Separate refund counts from refunded value reported in the store currency, attribute each refund to its order date as well as its refund date, and search for clusters recurring by product, reason or period, excluding records with missing order links from the rates and reporting them separately.
Return the refund breakdown and action list, then verify the patterns 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.
Assemble the order history with order dates and identifiers, the refund events with their dates, amounts and currencies, the reason codes recorded on each refund, and the product identifiers the refunded line items refer to, for the merchant's stated analysis window.
Separate refund counts from refunded value reported in the store currency, attribute each refund to its order date as well as its refund date, and search for clusters recurring by product, reason or period, excluding records with missing order links from the rates and reporting them separately.
Deliver the refund breakdown with an action list, reconcile the total refunded value and count in the report against the refund event export before publishing, and state which date basis each figure uses.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
They are excluded from the rates and reported as a separate unlinked group. Unlinked refunds cannot be attributed to any product or period, so including them would distort the clusters. Their total value still counts in the reconciliation so nothing goes silently missing.
All amounts are reported in the store currency with the original currency noted per refund. Summing mixed currencies as raw numbers produces totals that mean nothing. The conversion basis used is stated in the report.
The report's total refunded value and refund count are compared with the refund event export for the same window. This catches assembly errors such as dropped or double-counted events. Any gap is resolved before the report is published.
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.