01
Step 1
Pull order IDs with their creation and status timestamps, line values, currency and any refunds on record, then deduplicate to one row per order ID before counting anything.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Analyze order volume and composition
Orders are exported more than once, so the same order appears under several statuses and the totals drift. In this case, the immediate task is to analyze order volume and composition. The workflow should produce an order report that deduplicates records, states which statuses count and groups the result by the requested dimension.
Topic
Order Analytics and Reporting
Target keyword
shopify order analytics
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 order volume and composition.
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: [order IDs with creation and status timestamps, line values, currency and any refunds on record, deduplicated to one row per order ID]. State which statuses and which date basis count, apply that rule to every row rather than to a single export, and group by the requested dimension with each group's order count and value shown side by side.
Return the order report with its inclusion rules 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
State which statuses and which date basis count, apply that rule to every row rather than to a single export, and group by the requested dimension with each group's order count and value shown side by side.
03
Step 3
Deliver the order report with its inclusion rules printed on it, then reconcile the order count and value against the merchant's records and list every excluded order with the reason.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Should test orders appear in the analysis?
Exclude them and say so on the report, because mixing them with real orders distorts both volume and value. Identifying them from the records supplied is more reliable than filtering on a name pattern that may also catch real customers.
Why do two exports show different counts?
Usually a different status or date basis, taken at a different moment. Compare the inclusion rules before assuming a data error, then rebuild both from the same order ID list to confirm the difference.
How should refunds appear in the order report?
Report gross and refunded amounts separately, then apply the merchant's stated net rule in one place. Netting row by row hides how much revenue was returned and makes later reconciliation harder.
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.