Alerts that nobody claims simply disappear, and the merchant has no rule for when they should move upward. In this case, the immediate task is to define when unresolved alerts should escalate. The workflow should produce an alert management specification and message templates listing every level, the trigger that moves an item up and what each level must do.
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 define when unresolved alerts should escalate.
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 severities with stated response expectations, escalation contacts per severity and coverage window, team coverage hours and handoff paths, and acknowledgement records with the timestamp the escalation clock starts from]. Escalate an item once time elapsed from that start timestamp passes the severity's stated response expectation, or when no acknowledgement exists at the end of it, counting waiting time only inside coverage hours unless the severity is listed as always-on and skipping items already acknowledged or marked resolved, while recording which rule moved each item up.
Return an alert management specification and message templates listing every level and the condition that moves an item upward 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 alert severity with its stated response expectation, the contact named for each severity and coverage window, the hours each team covers and the handoff path between them, and the acknowledgement record that proves an alert was claimed along with the timestamp the escalation clock starts from.
Escalate an item once time elapsed from that start timestamp passes the severity's stated response expectation, or when no acknowledgement exists at the end of it, counting waiting time only inside coverage hours unless the severity is listed as always-on and skipping items already acknowledged or marked resolved, while recording which rule moved each item up.
Deliver the alert specification and message templates listing every level with its trigger, named owner, required action and the notice returned to earlier handlers, then verify by replaying the store's open alert records through the ladder and confirming each lands on exactly one level, every level has a named contact and no item waits past its expectation.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
It starts at the timestamp the alert was first delivered to a named channel, not when the underlying condition appeared, because an alert nobody received cannot be answered. Restarts are recorded only when ownership changes, so a handoff never silently resets the wait.
Waiting time is counted only inside the hours the responsible team states it covers, unless the severity is marked always-on. An item that would escalate overnight is queued to the next coverage window and flagged, so it is neither lost nor escalated to an unavailable contact.
Only where the merchant has declared a severity that jumps straight to a named contact, and that exception is written into the specification. Otherwise every item climbs one level at a time, which keeps each handler able to say what was already tried.
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.