01
Step 1
Pull spend, impressions, clicks, orders and revenue for every campaign over one date range agreed in advance, keeping the campaign naming, the currency and the status of each campaign exactly as the source exports record them.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Analyze ad performance across campaigns
Campaign numbers sit in exports with mismatched date ranges, so nothing explains where performance breaks down. In this case, the immediate task is to analyze ad performance across campaigns. The workflow should return a breakdown over one consistent date range, with each rate stated alongside its denominator and priorities ranked by impact.
Topic
Ad Performance Analytics
Target keyword
shopify ad analytics tool
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 analyze ad performance across campaigns.
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: [spend, impressions, clicks, orders and revenue per campaign over one agreed date range, plus the campaign naming, currency and status recorded in the source exports]. Compute click-through rate, cost per click, conversion rate and return on spend with the denominator written beside each, compare campaigns on those rates together with their volume, and set aside any campaign whose export does not cover the full agreed range instead of scaling its figures to fit.
Return the breakdown with priorities ranked by impact and each figure verified against the supplied source data 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
Compute click-through rate, cost per click, conversion rate and return on spend with the denominator written beside each, compare campaigns on those rates together with their volume, and set aside any campaign whose export does not cover the full agreed range instead of scaling its figures to fit.
03
Step 3
Deliver the breakdown with priorities ranked by the impact each campaign can move, then verify every figure against the source export and confirm that the sum of campaign spend equals the account spend for the same range.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How is a campaign with a partial export handled?
It is excluded from the ranked comparison and listed separately with the range it does cover, because scaling a partial range up to the full window invents activity the account never bought. It returns to the ranking once its export covers the agreed range.
Why rank by impact rather than by worst rate?
The worst-looking rate often sits on a campaign too small to change the account result, while a moderate weakness on a large campaign costs far more. The ranking pairs each rate with the campaign's share of spend and orders so the first item is the one worth acting on.
What confirms the breakdown is complete?
Summing campaign spend and orders and matching both to the account totals for the same range, with any campaign present in the account but absent from the exports listed as missing. A total that does not tie back means rows were dropped or counted twice somewhere.
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.