Optimization changes have accumulated with no log tying each one to the results behind it, and metric definitions differ between reports. In this case, the immediate task is to develop evidence-based advertising optimization actions. The workflow should return an action list where each entry cites its supporting record and review date.
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 develop evidence-based advertising optimization actions.
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: [campaign results over the evaluation window, the stated objective, the change log of campaign and page edits, and the definition and source of every reported metric]. Attach each proposed action to the record that supports it, discard any action resting on an impression, and where two metrics conflict name the one tied to the current objective as decisive and report the other as context.
Return the action list with checks and review dates, confirmed against the supplied performance 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.
Bring together campaign results over one merchant-defined window, the stated objective, the change log of edits made to campaigns and pages, and the definition and source of every reported metric so figures sharing a name can be told apart.
Attach each proposed action to the record that supports it, discard any action resting on an impression, and where two metrics conflict name the one tied to the current objective as decisive and report the other as context.
Deliver the action list with the supporting record, the check that would show the action worked and a review date for each, then confirm the list against the performance export and mark every action whose change log entry postdates the results it cites.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
An edit to targeting, creative or a page can move results on its own, so an action proposed without that context may be reacting to the store's own change; the log also gives the review date something to compare against.
Record the definition and source of each, then decide on the metric tied to the current objective and report the other alongside it, because reconciling two differently defined numbers into one usually hides the difference that matters.
It names the record behind it and the check that would show it worked, with a date attached; a recommendation without a supporting figure stays labelled as a suggestion, which is honest about how much weight it carries.
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.