A merchant ships through several carriers whose portals describe the same event differently, so staff read three screens to answer one question. In this case, the immediate task is to consolidate shipment tracking information. The workflow should produce one readable timeline per order that keeps the source of every event visible and resolves conflicts.
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 consolidate shipment tracking information.
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: [tracking numbers and carrier references per order, raw scan events with local timestamps and timezones from each carrier portal, each carrier's status vocabulary, the store timezone, and the merchant's staleness limit]. Merge those events into one chronological timeline per order, keeping the source and the original wording on every entry, collapsing entries from different carriers that share the same scan location and event time into a single event, and where two sources disagree on the current state taking the later timestamp over the earlier one while recording the discarded reading beside it.
Return a consolidated tracking view with source attribution per event 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 each order in the merchant-defined window, the tracking numbers and carrier references on file, the raw scan events each carrier portal returns with their local timestamps and timezones, and the status vocabulary each carrier uses, converting every timestamp to the store timezone before any comparison.
Merge those events into one chronological timeline per order, keeping the source and the original wording on every entry, collapsing entries from different carriers that share the same scan location and event time into a single event, and where two sources disagree on the current state taking the later timestamp over the earlier one while recording the discarded reading beside it.
Deliver one readable timeline per order with the source of each event visible, reconcile the event count against the sum of events each carrier portal returned for the same window, and list every order whose timeline rests on a single source or whose latest event is older than the merchant's stated staleness limit.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
The event with the later timestamp wins for display, and the discarded reading stays recorded beside it so the disagreement remains visible, because carriers publish the same physical scan at different times. The rule does not apply when the later event comes from a source the merchant has marked unreliable, in which case the pair is escalated for a person to decide.
Keep them in a separate band on the same screen, because staff comments are not carrier confirmations and placing them inline makes a merchant's guess look like a carrier event. The boundary is that anything the merchant writes carries its author, while anything a carrier publishes carries the source name.
Show it as awaiting reference with the carrier and dispatch date that should supply one, since reporting it as in transit states something the records do not support. The order leaves that state only when a tracking number appears in the supplied records, not when a shipment is merely expected.
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.