Alerts inform the team but rarely turn into work anyone owns. In this case, the immediate task is to convert actionable alerts into owned follow-up tasks. The workflow should produce an alert management specification and message templates, with each proposed task carrying an owner, a record reference and a closure condition.
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 convert actionable alerts into owned follow-up tasks.
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: [alert types with thresholds, current recipients and escalation paths, the order, product, customer and ticket records each alert can reference, the available roster of people and roles, and the merchant's stated closure condition per alert type]. Convert only alerts a named person can act on into tasks, giving each one exactly one accountable owner, a reference to the record it came from, a next action written as an instruction and a closure condition, while logging informational, duplicate and already-resolved alerts as no-task items with the reason stated.
Return an alert management specification and message templates with every proposed task checked against the supplied records 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 alert types with their thresholds, the recipients and escalation paths currently in use, the order, product, customer and ticket records each alert can point to, the roster of people and roles available to take work, and the closure condition the merchant states for every alert type.
Convert only alerts a named person can act on into tasks, giving each one exactly one accountable owner, a reference to the record it came from, a next action written as an instruction and a closure condition, while logging informational, duplicate and already-resolved alerts as no-task items with the reason stated.
Deliver the alert management specification and message templates in which every proposed task carries an owner, a record reference and a closure condition, then verify against the supplied alert and record extracts that the task count equals actionable alerts minus logged no-task items, every reference resolves to a real record and no task is left without an owner.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
One named person stays accountable even where others contribute, because a task owned by a group tends to wait for everyone. Contributors are listed as additional contacts, and the owner is the one who reports the closure condition as met.
Each task carries the alert identifier, the source record reference and the timestamp the alert fired. Those three let anyone reopen the evidence later, while a task that only describes the symptom forces the next person to search again.
When it is informational, duplicates an open task, or is already resolved by the time it is read. Such items are logged with a reason rather than dropped, so the count of suppressed alerts stays visible and nobody assumes coverage is complete.
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.