Sales and stock are reviewed separately, which hides products overstocked in one variant and short in another. In this case, the immediate task is to compare product sales with inventory position. The workflow should produce an inventory health analysis and prioritized actions, setting sell-through beside stock on hand for each product in the period.
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 product sales with inventory position.
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: [net sold units per product for the agreed period, closing stock on hand, the variant-to-product mapping, and the merchant's sell-through definition]. Place net sold units beside closing stock for each product and for the variants inside it, compute sell-through as net units sold divided by the units available over the period with the same definition everywhere, and flag surplus where closing stock runs far ahead of the period's sales and shortage where sales outran the units recorded as available, setting aside products with no stock record at either period boundary.
Return an inventory health analysis and prioritized actions 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.
Pull, for one agreed reporting period, each product's sold units net of returns, its stock on hand at the period end, the variant-to-product mapping, and the sell-through definition the merchant uses, counting a unit as sold on the order date recorded in the export.
Place net sold units beside closing stock for each product and for the variants inside it, compute sell-through as net units sold divided by the units available over the period with the same definition everywhere, and flag surplus where closing stock runs far ahead of the period's sales and shortage where sales outran the units recorded as available, setting aside products with no stock record at either period boundary.
Deliver an inventory health analysis with one row per product plus a separate block for the variants driving each flag, add prioritized actions, and reconcile the summed sold units and closing stock with the order and inventory exports before publishing.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Returned units are subtracted from sold units in the period where the return was recorded, because they re-enter stock; using gross sales overstates consumption and makes a well-stocked product look short. A return landing after the period end is noted beside the figure rather than pushed back into a closed number.
A parent product can look balanced while one size sells out and another barely moves. The report rolls up to the product for the ranking, then reopens the variants behind each flag so the action, whether reorder, rebalance or markdown, is written against the variant that actually needs it.
When the product has no stock record at either period boundary, or when its only movements in the period are manual adjustments rather than sales. Those products are listed with the quantities that do exist and marked as not yet comparable instead of being ranked alongside products measured on a full basis.
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.