A merchant has parcels whose tracking has not moved for days and must decide whether to claim or wait for a scan. In this case, the immediate task is to investigate potentially lost shipments using event evidence. The workflow should produce a per-parcel judgement separating stalled movement from a reporting gap, with the claim trigger applied.
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 potentially lost shipments using event evidence.
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: [the full scan history per parcel with timestamps and locations, carrier references and service levels, last known locations, declared contents and values, support correspondence, and the merchant's silence period and claim trigger]. Judge whether the evidence shows stalled movement, meaning a last scan outside the expected network path, no onward scan for the merchant's stated silence period, or a return or exception scan, or merely a reporting gap where the carrier feed has not updated while other parcels on the same service also went quiet, apply the merchant's stated claim trigger to the stalled cases only, and mark any parcel whose history is incomplete as undetermined rather than lost.
Return a lost-package assessment with a recommended next step per parcel 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.
Assemble, for each parcel under review, the complete scan history with timestamps and locations, the carrier reference and service level, the last known location, the declared contents and value used in any claim, and the support correspondence already exchanged with the customer and the carrier.
Judge whether the evidence shows stalled movement, meaning a last scan outside the expected network path, no onward scan for the merchant's stated silence period, or a return or exception scan, or merely a reporting gap where the carrier feed has not updated while other parcels on the same service also went quiet, apply the merchant's stated claim trigger to the stalled cases only, and mark any parcel whose history is incomplete as undetermined rather than lost.
Deliver a per-parcel assessment naming the classification, the evidence it rests on and the recommended next step of waiting for the next scan, opening a carrier trace or filing a claim, reconcile the parcels assessed against the shipments with no delivery scan in the window, and note each case where a replacement or refund was issued before the carrier responded.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
A last scan outside the expected path, no onward scan for the merchant's stated silence period, or a return or exception scan, rather than silence alone. Silence on one parcel while other parcels on the same service also went quiet points to a feed gap, which is classified undetermined instead of lost.
No, it confirms a carrier event rather than that the customer holds the item. Where the customer disputes it, the assessment records both statements, keeps the case open and follows the stated claim process, because the scan image and location point are evidence the carrier controls.
Only where the merchant's rules allow it, and then with the decision, the reason and the claim reference recorded so the outcome can be reconciled later. Shipping without that record leaves the claim and the replacement impossible to tie together and unverifiable afterwards.
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.