01
Step 1
Record the decisions the dashboard has to support each day, the metrics and breakdowns each decision needs, the source report standing behind every metric, and the reporting timezone and currency the sources share.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Build a campaign performance dashboard
Reporting is scattered and no single view answers the daily questions, so the metrics to show must follow the decisions they support. In this case, the immediate task is to build a campaign performance dashboard. The workflow should return a layout grouped by funnel stage, with a definition and source for every metric.
Topic
Ad Performance Analytics
Target keyword
shopify ad performance dashboard
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 build a campaign performance dashboard.
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 daily decisions to support, the metrics and breakdowns each decision needs, the source report behind every metric, and the reporting timezone and currency the sources share]. Group the metrics by funnel stage with one denominator written beside every rate, and mark any metric whose source report is missing, delayed or collected on a different calendar as unavailable rather than zero so no tile shows a figure that no record supports.
Return the dashboard layout with metric definitions, checked against the supplied reporting sources 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
Group the metrics by funnel stage with one denominator written beside every rate, and mark any metric whose source report is missing, delayed or collected on a different calendar as unavailable rather than zero so no tile shows a figure that no record supports.
03
Step 3
Deliver the dashboard layout with a definition and a source for every metric, then verify it by rebuilding one reporting window from the raw source reports and confirming that each tile reproduces the same figure.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How should a metric with no source report be shown?
As unavailable rather than zero, because a zero behaves like a real measurement and gets acted on. The tile carries the missing source name and the last window it did arrive for, so a reader can tell a genuine drop from a broken feed.
Why state the denominator beside each rate?
The same rate name is computed over different bases in different reports, and a figure shown without its base cannot be compared across tiles or weeks. Writing the denominator on the tile also makes the number reproducible from the raw source when someone questions it.
What belongs in the drill-down rather than the first screen?
Anything needed to explain a change rather than to notice it, such as per-campaign or per-device splits. The first screen carries only the figures that decide whether action is needed today, so the view stays readable at a glance.
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.
Track advertising spend using consistent reporting periods
Report conversion rates for advertising traffic
Analyze ad performance across campaigns
Create a sales dashboard with clear metric definitions
Consolidate TikTok advertising performance data
Develop evidence-based advertising optimization actions
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.