01
Step 1
Take the price rendered on the storefront for each affected variant, the catalog price record for the same variant, the active currency and rounding settings, and any compare-at or discount field that feeds the display.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Diagnose incorrect or inconsistent displayed product prices
Storefront prices diverge from the catalog on some products, and the merchant cannot tell which is wrong. In this case, the immediate task is to diagnose incorrect or inconsistent displayed product prices. The workflow should produce a prioritized product issue report tracing each wrong figure to its source field, separating display faults from data errors.
Topic
Product Data Quality and Audits
Target keyword
shopify product price display issues
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 incorrect or inconsistent displayed product prices.
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: [the price rendered on the storefront per affected variant, the catalog price record for the same variant, the active currency and rounding settings, and any compare-at or discount field that feeds the display]. Trace each wrong figure back to the field that produced it, decide whether the fault sits in the display layer or in the stored record, and mark the case as a data error wherever the record itself is the source of the wrong figure.
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
Trace each wrong figure back to the field that produced it, decide whether the fault sits in the display layer or in the stored record, and mark the case as a data error wherever the record itself is the source of the wrong figure.
03
Step 3
Deliver a prioritized product issue report giving the rendered value, the recorded value, the responsible field and the suggested fix per case, then re-check each corrected product against the catalog record and list any case where the two still differ.
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 rounding difference told from a real error?
A difference within the rounding step the merchant has stated, appearing on every variant alike, is expected behaviour and should be recorded rather than fixed. A single variant off by more points at one specific field.
Should a compare-at price be checked against the same rule?
No, it is a reference figure and may legitimately sit above the price. Check only that it stays higher than the current price and that nothing renders where the record leaves it empty.
What if the storefront and the record agree but both look wrong?
The fault is then in the data rather than the display, so raise it as a price error against the record. Fixing the template in that case hides the wrong figure behind a render that now looks correct.
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.