01
Step 1
Take a dated catalog snapshot to audit against, the checklist of checks to run, the findings recorded in the previous run, and the product scope and exclusions stated for this run.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Run a repeatable product data audit
The merchant wants one product audit that can be rerun after each catalog change instead of ad hoc spot checks. In this case, the immediate task is to run a repeatable product data audit. The workflow should produce a prioritized product issue report in which every finding carries the evidence recorded during the pass and this run's scope is stated.
Topic
Product Data Quality and Audits
Target keyword
shopify product audit 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 run a repeatable product data audit.
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: [a dated catalog snapshot, the checklist of checks to run, the findings recorded in the previous run, and the product scope and exclusions stated for this run]. Run the same checklist over every product in scope without reinterpreting it mid-pass, capture the evidence behind each finding as it is found, and tag every prior finding as closed, still open or recurring since the last run.
Return a prioritized product issue report with evidence and suggested fixes 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
Run the same checklist over every product in scope without reinterpreting it mid-pass, capture the evidence behind each finding as it is found, and tag every prior finding as closed, still open or recurring since the last run.
03
Step 3
Deliver a prioritized product issue report stating the snapshot date, the scope covered and the number of products checked, then reconcile that count against the snapshot and list any checklist item that could not be judged from the snapshot alone.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why audit against a snapshot instead of the live catalog?
A snapshot freezes what was actually checked, so any finding can be reproduced later. Auditing live data means products can change between the check and the report, leaving findings that nobody can confirm.
How should findings from the previous run be treated?
Re-test each one and mark it closed, still open or recurring. A finding that reappears points at the import or the workflow that keeps producing it, not at the product itself, and needs a different fix.
What if a checklist item cannot be judged from the data at hand?
Mark it as not assessable instead of passing it by default. An unverifiable item recorded as clean makes the run look more complete than it is, and the gap stays invisible until someone re-checks it.
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.
Design recurring audits for product data quality
Summarize catalog quality issues by product and severity
Assess listing completeness using explicit review criteria
Investigate missing or confusing variant information on a page
Diagnose incorrect or inconsistent displayed product prices
Identify missing or invalid variant prices
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.