The store can only confirm a handful of delivery states, yet messages go out on events nobody has verified. In this case, the immediate task is to create delivery-status notifications from reliable evidence. The workflow should produce one message per confirmable state with the evidence behind it and rules that suppress repeated events.
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 create delivery-status notifications from reliable 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 delivery states the store can confirm, the evidence proving each state such as the acceptance scan or delivery confirmation, the templates in use, and the orders whose delivery events repeated]. Write one message per confirmable state quoting the evidence behind it, require that evidence before the message fires so a label created event never announces dispatch, and record per order which delivery messages have been sent so a repeated scan suppresses the duplicate.
Return the templates and event rules 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 delivery states the store can confirm, the evidence that proves each one such as the carrier acceptance scan or the delivery confirmation, the templates in use, and for one merchant-defined window the orders whose delivery events repeated.
Write one message per confirmable state quoting the evidence behind it, require that evidence before the message fires so a label created event never announces dispatch, and record per order which delivery messages have been sent so a repeated scan suppresses the duplicate.
Deliver the templates with their evidence rules and suppression entries, replay the window's orders through them and list any state a message claims but no record can confirm, then verify against the supplied records that each order received one message per state.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Only the states the store can prove with evidence from the carrier, typically acceptance, delivery attempt and delivery, since a message on an unconfirmed state promises movement that may never happen; a state with no evidence rule in the specification is dropped rather than sent on trust.
A label only means the parcel was prepared, not that the carrier holds it, so announcing dispatch there tells the customer to expect tracking that does not exist yet; the trigger is the carrier acceptance event, and the label event is recorded for internal use only.
Each order records the delivery messages it has already been sent and a repeated scan of the same state sends nothing, because duplicate delivery notices are the most common complaint about shipping automation; a genuinely new state always sends, so a failed attempt followed by a delivery produces two messages.
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.