01
Step 1
Collect attributed revenue and spend per campaign over a defined baseline period and the current period, with the attribution setting and window in use, the reporting lag of the revenue source and the currency each figure is stated in.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Monitor material declines in attributed ROAS
ROAS is watched loosely, and small samples or reporting lag make an ordinary dip look like a collapse; the attribution setting in use is recorded. In this case, the immediate task is to monitor material declines in attributed ROAS. The workflow should return alert rules requiring minimum spend and a sustained drop, plus a review step.
Topic
Ad Performance Alerts
Target keyword
shopify roas alerts
Copyable AI prompt
A prompt you can drop directly into Spark
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.
ai-prompt.txt
Act as a Shopify operations specialist.
Help me monitor material declines in attributed ROAS.
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: [attributed revenue and spend per campaign for the baseline and current periods, the attribution setting and window in use, the revenue source's reporting lag, and the currency of each figure]. Express ROAS as attributed revenue divided by spend using one attribution setting throughout, and raise an alert only where the current period clears the merchant's minimum spend, stays below baseline for the whole persistence window and falls outside the range the supplied history supports.
Return the ROAS alert rules with the review step for each, with thresholds verified against the supplied history 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.How to solve
A recommended resolution workflow
Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
02
Step 2
Express ROAS as attributed revenue divided by spend using one attribution setting throughout, and raise an alert only where the current period clears the merchant's minimum spend, stays below baseline for the whole persistence window and falls outside the range the supplied history supports.
03
Step 3
Deliver the ROAS alert rules with the baseline, minimum spend, persistence window and review step for each, then replay them against the supplied history and report both the alerts that would have fired and the periods excluded by the reporting lag.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why require a minimum spend before alerting?
A campaign with few orders can swing between extremes without anything having changed, so the minimum spend keeps the alert on movements the numbers can actually support; below it the period is reported as insufficient evidence instead.
How should the baseline be chosen?
From a comparable earlier period under the same attribution setting, because switching attribution silently changes which orders count and would make the baseline and the current period measure different things.
What does the review step check first?
Whether revenue for the recent part of the period has finished reporting, since a drop concentrated in the newest days usually closes once the lag passes, and pausing delivery on it would undo a campaign that is performing.
Related scenarios
Continue with adjacent or same-topic scenarios
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
Next step
Want these AI scenarios embedded directly into daily operations?
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.