01
Step 1
Gather the spend series per campaign with its period boundaries, the campaign structure and delivery status, every scheduled change with its effective date, the seasonality the merchant has recorded and the reporting lag of the source.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Detect unusual advertising spend patterns
Spend moves in ways the team cannot explain, and the campaign structure, scheduled changes and known seasonality needed to judge it are on hand. In this case, the immediate task is to detect unusual advertising spend patterns. The workflow should separate genuine anomalies from planned changes, each with evidence and a follow-up check.
Topic
Ad Performance Alerts
Target keyword
shopify ad spend anomaly detection
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 detect unusual advertising spend patterns.
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: [the per-campaign spend series with its period boundaries, the campaign structure and delivery status, every scheduled change with its effective date, the merchant's recorded seasonality and the source reporting lag].
Compare each period against the range the supplied history supports for that campaign after removing scheduled changes and the still-lagging tail, calling a movement an anomaly only where it persists across enough periods to rule out a reporting gap.
Return the findings with evidence and a follow-up check for each, verified 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.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
Compare each period against the range the supplied history supports for that campaign after removing scheduled changes and the still-lagging tail, calling a movement an anomaly only where it persists across enough periods to rule out a reporting gap.
03
Step 3
Deliver the findings as confirmed anomaly, planned change or reporting gap, each with the periods compared, the figures behind the verdict and a follow-up check naming the record that would confirm it, then reconcile the campaign totals with the account total for the same window.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How does a planned change get separated from a real anomaly?
Every scheduled change carries an effective date, and movements starting at that date are attributed to it first, because a budget edit explains a spend jump completely and calling it an anomaly sends the team looking for a cause already on file.
Why check delivery status before reporting an anomaly?
A campaign that stopped or resumed delivery changes spend without anything having happened to demand, so the status is read first; reporting that as a market shift produces a diagnosis no later figure will support.
What makes a single unusual period worth reporting?
Persistence across enough consecutive periods to clear the reporting lag, since one odd period is often data that had not finished arriving and the follow-up check is simply to reread it once the lag closes.
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.