01
Step 1
Collect the orders and returns available, the currency and timezone settings, the reporting window and the sales definition the merchant wants used, covering the treatment of discounts, taxes, shipping and gift cards.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Build a consistent store analytics workflow
Each period is reported with a slightly different definition of sales, so the numbers cannot be compared. In this case, the immediate task is to build a consistent store analytics workflow. The workflow should produce a sales report with definitions and reconciliation notes, using the merchant's orders, returns, currency and timezone settings.
Topic
Sales and Store Analytics
Target keyword
shopify analytics app
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 consistent store analytics workflow.
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 orders and returns available, the currency and timezone settings, the reporting window, and the sales definition covering discounts, taxes, shipping and gift cards]. Fix one definition per measure, meaning the date field, the order statuses counted, whether refunds reduce the period they were issued in or the original order period, and the currency conversion basis, then apply it unchanged to every period and record its version and effective date so older reports stay interpretable.
Return a sales report with definitions and reconciliation notes 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
Fix one definition per measure, meaning the date field, the order statuses counted, whether refunds reduce the period they were issued in or the original order period, and the currency conversion basis, then apply it unchanged to every period and record its version and effective date so older reports stay interpretable.
03
Step 3
Deliver the sales report with a definition block, a reconciliation against the order export naming every adjustment and its reason, and the list of records excluded as incomplete, then verify that reported totals tie back to the source orders within the stated differences.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why fix the sales definition before reporting?
Gross and net treat discounts, refunds and taxes differently, so periods built on shifting definitions cannot be compared and totals get disputed. One definition, versioned with an effective date, keeps every later period comparable and lets an older report still be read correctly.
Should refunds reduce the original order period?
Choose one treatment and state it. Reducing the original period keeps a sale and its refund together, while reducing the issue period matches cash; mixing the two across periods makes a quiet month look recovered, so the choice is recorded rather than left implicit.
How are currency and timezone handled?
State one reporting currency with the conversion basis, meaning the store rate at order time or the rate on the reporting day, and one timezone for day boundaries, then apply both to every period. Mixing either places the same order in different windows across reports.
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.