Ciwi
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant

Identify the segments driving changes in AOV

Average order value has moved, but the change could come from a different mix of customers or from real movement inside each group. In this case, the immediate task is to identify the segments driving changes in AOV. The workflow should produce an AOV analysis and improvement hypotheses tracing each finding back to those order records.

Topic
Average Order Value Analysis
Target keyword
shopify aov analysis
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 identify the segments driving changes in AOV.

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 lines with quantities and prices, the customer segment for each order, applied discounts, refund records, and the available comparison periods with the sales basis used for each]. Separate a shift in segment mix from real movement inside a segment by recomputing the measure within each segment for both periods first and then checking whether that segment's share of orders also moved, naming a driver only where both point the same way.
Return an AOV analysis and improvement hypotheses tracing each finding back to those order records 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.
Use in Spark
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.

01

Step 1

Collect the order lines with quantities and prices, the customer segments each order belongs to, the discounts applied, the refund records, and the comparison periods available with the sales basis used for each.

02

Step 2

Separate a shift in segment mix from real movement inside a segment by recomputing the measure within each segment for both periods first and then checking whether that segment's share of orders also moved, naming a driver only where both point the same way.

03

Step 3

Deliver the AOV analysis and improvement hypotheses tracing each finding back to those order records, then verify that segment figures sum to the reported total, that each named driver is supported by order lines from the supplied records and that segments too small to support a conclusion are listed as inconclusive.

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 mix shift separated from a real change?

Recompute the measure inside each segment for both periods, then check whether that segment's share of orders moved as well. Movement with a stable share points inside the segment, while a shifting share explains the change without any behaviour change.

Do discounts belong in the calculation?

State the convention before computing and apply it to every period, because a gross basis and a net basis answer different questions. Switching conventions between periods produces a change that exists only on paper, which is why the basis is named in the output.

Which segments deserve attention first?

Those holding a meaningful share of orders in the supplied records, since a small segment can swing dramatically on a handful of purchases. Segments too thin to support a reading are listed as inconclusive rather than ranked.

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.

Open Spark product pageBack to Spark scenario library