Minor rounding differences keep firing notifications, so the team has started ignoring the whole channel. In this case, the immediate task is to alert on material inventory discrepancies. The workflow should produce an inventory reconciliation and proposed correction file tied to the merchant's own thresholds and owners.
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 alert on material inventory discrepancies.
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: [both comparison records with extraction timestamps, the merchant's stated materiality threshold as a unit gap and a value gap per SKU, the location scope, the alert owner and channel per type, agreed suppression windows, and the recent alert history].
Compare quantities by SKU and location inside one unit of measure, treat a difference inside the merchant's stated tolerance as non-alerting and log it, aggregate differences that stay sub-threshold but recur across consecutive comparisons into a single drift item, and raise one alert per breach naming both figures, the gap, whether it risks oversell or hides sellable stock, and the owner.
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 both comparison records with their extraction timestamps, the merchant's stated materiality threshold expressed as a unit gap and a value gap per SKU, the location scope, the owner and channel assigned to each alert type, the agreed suppression windows for known maintenance, and the recent alert history so a repeating difference can be recognised.
Compare quantities by SKU and location inside one unit of measure, treat a difference inside the merchant's stated tolerance as non-alerting and log it, aggregate differences that stay sub-threshold but recur across consecutive comparisons into a single drift item, and raise one alert per breach naming both figures, the gap, whether it risks oversell or hides sellable stock, and the owner.
Deliver an inventory reconciliation with the alert list showing SKU, location, both quantities, gap, threshold applied, owner and first action, plus a proposed correction file, then confirm every alert row traces to a comparable pair in both records and that suppressed items still appear in the log with their reason.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Only when the merchant has defined a shared cause, such as one feed failing for a location; otherwise each SKU and location gets its own alert, so an owner can act on a single correction instead of investigating a group.
Keep the tolerance the merchant stated as the bar for sending, but log everything below it and promote a difference to an alert when it recurs across consecutive comparisons, so silent drift is still surfaced while one-off rounding stays quiet.
Act without reopening the records: it must carry both quantities, the gap, the threshold that was breached and the proposed correction row, and it should name the owner who can reconcile the two sources rather than a channel nobody monitors.
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.