A merchant only hears about late parcels once the customer writes in, by which point the promised date has already passed. In this case, the immediate task is to detect shipments that may exceed delivery expectations. The workflow should produce a watchlist of parcels near or past their committed date, tiered by urgency and paired with a message draft.
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 shipments that may exceed delivery expectations.
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: [promised delivery dates for open shipments, each shipment's latest scan with timestamp and location, destination region and service level, the merchant's early-warning lead time, and the stated silence period]. Flag a shipment as at risk when elapsed transit against its own promise has passed that early-warning lead time or the promised date has passed with no delivery scan, tier the result by whether the promise is already missed, is expected to be missed on the current trajectory, or has stalled with no scan for the merchant's stated silence period, and suppress any shipment already carrying a delivery scan.
Return a delay watchlist with urgency tiers and message drafts 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, for the merchant-defined monitoring window, the promised delivery date recorded for each open shipment, the carrier's latest scan with its timestamp and location, the destination region and service level, and the merchant's stated early-warning lead time.
Flag a shipment as at risk when elapsed transit against its own promise has passed that early-warning lead time or the promised date has passed with no delivery scan, tier the result by whether the promise is already missed, is expected to be missed on the current trajectory, or has stalled with no scan for the merchant's stated silence period, and suppress any shipment already carrying a delivery scan.
Deliver a watchlist ordered by urgency with one row per shipment showing the promise, the last scan, the days consumed and a draft customer message naming only what the records support, keep one open alert per shipment by closing the lower tier when a shipment escalates, and reconcile the shipments listed against the open fulfillment export for the same window.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
When elapsed transit has passed the merchant's stated early-warning lead time, so the customer hears from the store while a remedy is still available. Waiting for the date itself removes that window, and firing earlier than the lead time produces warnings the tracking evidence does not yet support.
Alerts are deduplicated per shipment and re-issued only when the tier changes or a new scan arrives, because repeated identical messages train recipients to ignore them. A shipment that resolves is closed with its resolution time rather than left open on the list.
No, the flag records that a promise is at risk rather than its cause. Cut-off times, incomplete addresses and internal handling produce the same pattern, so each row names the evidence it holds, meaning last scan location, elapsed days and the promise, and leaves cause to the merchant.
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.