01
Step 1
Gather each business rule with the product attributes it depends on, the affected collections, the field edits it makes, the stated exclusions, and an ordering that records which rule wins when several match the same product.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Define conditional catalog updates from business rules
Pricing and merchandising rules live in a spreadsheet, and nobody can say which products a rule would touch. In this case, the immediate task is to define conditional catalog updates from business rules. The workflow should produce a rule specification with sample outcomes and confirm the selected and excluded products against the merchant's records.
Topic
Product Workflow Automation
Target keyword
shopify rule based product updates
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 define conditional catalog updates from business rules.
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: [business rules with their dependent product attributes, affected collections, field edits per rule, stated exclusions, and the rule precedence order].
Translate every rule into explicit field-level conditions, run them against sample products to produce selected and excluded lists, and block the run whenever a product matches overlapping rules without a recorded precedence or depends on an attribute that is empty or malformed.
Return the rule specification with sample outcomes, then verify the selected and excluded products against the supplied 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.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
Translate every rule into explicit field-level conditions, run them against sample products to produce selected and excluded lists, and block the run whenever a product matches overlapping rules without a recorded precedence or depends on an attribute that is empty or malformed.
03
Step 3
Deliver the rule specification with sample outcomes showing each rule's selected and excluded products, verify the sample lists against the merchant's records, and confirm every overlapped product carries the deciding rule's edit.
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 sample products chosen for testing a rule?
Samples include products meant to match, products meant to be excluded, and boundary shapes such as empty or malformed attributes. Boundary products expose conditions the business phrasing hides. A rule that selects none of its intended samples is blocked from approval.
What is recorded when a rule changes a field?
The deciding rule, the prior value and the new value are recorded per product. This trail is what lets a later audit retrace why a field holds its current value. Products touched by no rule appear in the outcome with that reason instead of being omitted.
When must a rule be blocked instead of run?
Whenever a product matches overlapping rules with no recorded precedence, or depends on an empty or malformed attribute. Running anyway lets rules act on products they were never meant to touch. Blocked products are routed to review with the reason named, never skipped silently.
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.