Step 1
Collect the order lines for the period with their fulfilment and cancellation states, the stock movements recorded against each line, the manual adjustments with their reasons, and the reservation records held against those units.
Some orders shipped without reducing stock while others reduced it twice, leaving availability out of step with reality. In this case, the immediate task is to investigate differences between stock and order movements. The workflow should produce an inventory reconciliation and proposed correction file traced through the merchant's own order lines.
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 investigate differences between stock and order movements.
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 lines for the period with their fulfilment and cancellation states, stock movements recorded per line, manual adjustments with their reasons, and reservation records against those units]. Confirm for every order line that exactly one deduction of the ordered quantity exists in the stock movements, treating a cancellation or refund as requiring its own restoring movement, and classify each line as missing, duplicated, unrestored or correctly matched rather than netting the differences together.
Return an inventory reconciliation and proposed correction file verified 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.
Collect the order lines for the period with their fulfilment and cancellation states, the stock movements recorded against each line, the manual adjustments with their reasons, and the reservation records held against those units.
Confirm for every order line that exactly one deduction of the ordered quantity exists in the stock movements, treating a cancellation or refund as requiring its own restoring movement, and classify each line as missing, duplicated, unrestored or correctly matched rather than netting the differences together.
Deliver an inventory reconciliation with one row per affected line carrying the ordered quantity, the deductions found, the difference and the proposed correction, apply automatic treatment only to the defined cancellation state and route everything else to review, and verify that corrected movements bring stock back to the order-derived position.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
By matching movements to order lines instead of counting deductions: one line should carry one deduction of its quantity, so a second movement sharing the same order reference and timestamp pattern is a duplicate. A movement tied to a different order line is a genuine second sale.
Because the deduction was applied and the restoring movement never was. The cancelled or refunded line is expected to return its units, so where that movement is absent the line is listed as unrestored with the quantity to reinstate rather than written off as unexplained shrinkage.
Only those for a state the merchant defined in advance, such as a confirmed cancellation where the restoring movement is unambiguous. Exchanges, partial refunds and manual adjustments move stock on separate lines and are routed to review, since applying them automatically repeats the error that caused the mismatch.
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.