01
Step 1
Collect, for the decline period and a merchant-named comparison period, sessions, orders, units and net sales with the order status filter, currency and timezone stated, plus the availability log and the dated campaign and pricing changes.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Diagnose the main contributors to a sales decline
A merchant sees revenue fall against a comparable earlier period and needs to know which part of the funnel moved before acting. In this case, the immediate task is to diagnose the main contributors to a sales decline. The workflow should produce a decomposition into traffic, conversion and order value effects across matched periods the merchant can rebuild.
Topic
Sales Decline Diagnosis
Target keyword
shopify sales drop 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 diagnose the main contributors to a sales decline.
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: [sessions, orders, units and net sales for the decline and comparison periods with the stated order status filter, currency and timezone, plus the availability log and the dated campaign and pricing changes]. Decompose the movement into a traffic part, a conversion part and an order value part by holding the other two at the comparison-period level in turn, attribute each part to the product, channel or landing-page segments carrying the largest share, and mark any part distorted by stockouts or by a change in the reporting definition.
Return a decline explanation with the decomposition per part and next actions 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
Decompose the movement into a traffic part, a conversion part and an order value part by holding the other two at the comparison-period level in turn, attribute each part to the product, channel or landing-page segments carrying the largest share, and mark any part distorted by stockouts or by a change in the reporting definition.
03
Step 3
Deliver the decomposition with the contributing segments and next actions, reconcile the sum of the attributed changes against the observed net sales difference, and state explicitly where the parts fail to add up because segments overlap or a definition changed inside the window.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How are the three components separated?
Each part is measured with the other two held at the comparison-period level, so the traffic part is the change in sessions valued at the earlier conversion and order value, and so on. The boundary is overlap: the three parts rarely sum exactly to the total, and the residual is reported rather than forced to zero.
Can conversion improve while sales still fall?
Yes. A fall in sessions or average order value can offset a better conversion rate, so each part is measured separately before any conclusion is drawn. The report then names the part that moved most, instead of assuming one cause explains the whole decline.
Which period counts as comparable?
A period of the same length with similar seasonality and promotion activity, reported in the same timezone and currency. Where no such period exists, state that the comparison is approximate and show the differences in trading days and campaign days beside the decomposition.
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.