Spend figures from the platforms and the billing records disagree, partly because each report uses a different period and currency. In this case, the immediate task is to track advertising spend using consistent reporting periods. The workflow should return period totals and variance, flagging gaps or currency mismatches.
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 track advertising spend using consistent reporting periods.
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 fixed reporting calendar and currency, the merchant's stated spend basis, per-period spend rows from every platform export, and the matching billing records]. Total spend per period across sources and compute the variance between each platform figure and the billing record, flagging any period where a source has no rows, any period whose currency differs from the reporting currency, and any period where the platform figure and the billed figure disagree by more than the merchant's stated tolerance.
Return the spend view with period totals and variance, verified against the merchant's own billing 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.
Fix the reporting calendar, the reporting currency and the spend basis the merchant uses, then collect spend for those same periods from every platform export and every billing record, keeping the source name and the status of each record attached.
Total spend per period across sources and compute the variance between each platform figure and the billing record, flagging any period where a source has no rows, any period whose currency differs from the reporting currency, and any period where the platform figure and the billed figure disagree by more than the merchant's stated tolerance.
Deliver the spend view with period totals, variance and the flags, then verify it by confirming that every period in the calendar appears exactly once and that the flagged periods account for the whole difference between the sum of platform spend and the sum of billed spend.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
It is flagged as missing rather than counted as zero, because an empty export and a genuine zero-spend period look identical inside a total. The period still appears in the view so the gap in the calendar stays visible until the source is backfilled.
Every figure is converted into the merchant's stated reporting currency using one rate source and one conversion date per period, with the original currency recorded beside it. Converting inside the total hides the difference and leaves the variance row meaningless.
Platform exports measure what was served and billing records measure what was charged, and the two drift apart through adjustments, credits and fees. The variance row is what tells the operator whether a period total can be used for budgeting or has to be reconciled first.
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.