Meta exports arrive without every structural level the store needs, and their date ranges rarely match the store's reporting periods. In this case, the immediate task is to consolidate Meta advertising data for store reporting. The workflow should produce a unified reporting model and discrepancy log noting level mismatches and currency treatment.
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 consolidate Meta advertising data for store reporting.
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: [Meta account, campaign, ad set and ad level exports with breakdown columns, the account currency and timezone, the date range each export covers, and store-side order and product line records for the same periods]. Rebuild any structural level a breakdown export has dropped by using its identifier columns to restore parent fields before joining, align each export's date range to the store's reporting period while excluding or marking ranges that fall short of it, and record the exchange rate and rate date applied to every currency conversion.
Return a unified reporting model and discrepancy log noting level mismatches and currency treatment 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 the account, campaign, ad set and ad level exports with their breakdown columns, the currency and timezone the account reports in, the date range each export actually covers, and the store-side order and product line records for the same periods.
Rebuild any structural level a breakdown export has dropped by using its identifier columns to restore parent fields before joining, align each export's date range to the store's reporting period while excluding or marking ranges that fall short of it, and record the exchange rate and rate date applied to every currency conversion.
Deliver the unified reporting model and discrepancy log noting level mismatches, missing dimensions and currency treatment, then verify by checking row counts and spend subtotals against the original exports and confirming every joined figure names the level it was rebuilt at and the period it was aligned to.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Breakdown exports keep only the columns present at their own level, so parent fields such as campaign can be absent. Restoring them from identifier columns before the join prevents ad level rows being matched to the wrong parent and inflating a campaign total.
Either excluded from comparison or marked incomplete wherever it is shown, with the covered dates stated. Putting a partial period beside a full one makes a decline look like a performance change when it only reflects fewer days of data.
They stay in the report but always labelled as modelled, held apart from recorded conversions and never used as the reconciled figure. Treating an estimate as a recorded order removes the only check that the export is trustworthy.
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.