Carriers report many events, and the store has never decided which ones a customer actually needs to hear. In this case, the immediate task is to notify customers when shipment events are verified. The workflow should produce the announced events, their templates and destination rules so each recipient is told once.
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 notify customers when shipment events are verified.
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 carrier event types the store actually receives, the fulfilment records with one shipment per parcel, the contact details accepted on each order, and the shipments whose events repeated or arrived out of order]. Choose the events worth announcing from carrier acceptance through the final delivery attempt, bind one template and one destination rule to each, and send per parcel rather than per order so a split shipment tells the recipient which items are in the parcel that moved.
Return the event rules and templates 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 the carrier event types the store actually receives, the fulfilment records with one shipment per parcel, the contact details the customer has accepted on each order, and for one merchant-defined window the shipments whose events repeated or arrived out of order.
Choose the events worth announcing from carrier acceptance through the final delivery attempt, bind one template and one destination rule to each, and send per parcel rather than per order so a split shipment tells the recipient which items are in the parcel that moved.
Deliver the event rules with a template per announced event, replay the window's shipments through them and confirm each recipient is told once per parcel, then check the supplied fulfilment records for shipments that would send no message at all.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Only the events where the recipient gains something, starting with carrier acceptance and ending with the final delivery attempt, because announcing every scan buries the one that needs action; events the carrier reports but the recipient cannot act on stay silent and are still recorded for support.
Each parcel sends its own message naming the items it carries, so a customer receiving half an order is not told the order is complete; the order-level summary stays silent unless every parcel has reached the same event, which is checked against the fulfilment records.
A message is keyed to the event type and the parcel, so a late-arriving earlier event does not re-announce a state the recipient has already been told, since ordering by receipt time produces backwards updates; a delivery event always supersedes an attempt that arrives after 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.