A merchant sees products flip to unavailable overnight and cannot tell whether the stock really ran out or a sync failed. In this case, the immediate task is to detect products that become unavailable. The workflow should produce an alert per item recording when it stopped being sellable and whether the cause is a genuine sellout or a data error.
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 detect products that become unavailable.
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: [inventory quantities with last movement per SKU, published availability per variant across the channels in scope, the time each variant stopped being sellable, and the imports, syncs or bulk edits run in the window]. Confirm each case against the movement and import records as a genuine sellout where quantity fell through sales with a matching order, as a data error where quantity dropped with no matching sale, receipt or import, and as undetermined where the records in scope cannot distinguish the two.
Return an unavailable-product alert list with the cause per item 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.
Track, per SKU, the inventory quantity and its last movement, the published availability per variant across the channels in scope, the precise time each variant stopped being sellable, and the imports, syncs or bulk edits that ran in the same window.
Confirm each case against the movement and import records as a genuine sellout where quantity fell through sales with a matching order, as a data error where quantity dropped with no matching sale, receipt or import, and as undetermined where the records in scope cannot distinguish the two.
Deliver one alert per product naming the affected variants, the time observed, the last recorded movement and the cause, route data errors to the field or mapping that produced them rather than to purchasing, and reconcile the alerts against the count of products that changed to unavailable in the window.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
No, only the transition to not sellable alerts, while routine quantity changes go to the log. Alerting on each movement buries the change that actually stops sales, and the boundary is a variant that goes unavailable and returns inside the same sync cycle.
By matching the drop to a sale, a receipt or an import in the same window, since a fall with no matching record, or one that lands on every variant at once, points to a data error. Where the records cannot settle it, the case is marked undetermined rather than either.
The product, the affected variants, the time observed, the last recorded movement and the suspected cause, so the recipient can act without opening another screen. An alert naming only the product shifts the investigation back to whoever reads it.
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.