State changes fire several messages on different channels, and buyers receive repeats when nothing has moved. In this case, the immediate task is to create accurate order-status notification rules. The workflow should produce a mapping from each state change to one message and channel, sending only on verified evidence.
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 accurate order-status notification rules.
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: [every observable order state change, the message and channel currently sent on each one, the contact details the customer has accepted, and the orders whose state changed more than once in the review window]. Bind one message and one channel to each state change a customer acts on, keep internal processing states silent, and require a message to fire on the recorded state event only after it is verified, with a suppression entry per order so a state that repeats sends nothing the second time.
Return the notification 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 every order state change the store can observe, the messages currently sent on each one with the channel they use, the contact details the customer has accepted, and for one merchant-defined window the orders whose state changed more than once.
Bind one message and one channel to each state change a customer acts on, keep internal processing states silent, and require a message to fire on the recorded state event only after it is verified, with a suppression entry per order so a state that repeats sends nothing the second time.
Deliver the notification rules with a template per mapping, replay the window's orders through them and count the messages each order would receive, then confirm against the supplied records that no order is told the same thing twice and none is left without the message its state requires.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Only the changes the customer acts on, such as payment captured or shipment dispatched, while internal processing states stay silent, because messaging on every change trains customers to ignore the ones that matter; the boundary is written per state so the mapping can be tested rather than argued.
Each order keeps a record of the messages it has been sent and the state event that triggered them, so a state that re-enters or repeats sends nothing the second time; suppression is keyed to the order and the message rather than to the clock, so a genuine second shipment still sends.
The window's orders are replayed through the mapping and the messages each order would receive are counted, then compared with the state events in the order records, since a mapping tested only on a clean sample misses the repeats that cause complaints; any order receiving no message for a required state is fixed before release.
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.