01
Step 1
Take the description text per product with its product ID, the variant attributes that separate similar products, and the similarity threshold the merchant has set for calling two texts the same.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Detect repeated descriptions that obscure product differences
Several similar products share one block of description text, so buyers cannot see what differs. In this case, the immediate task is to detect repeated descriptions that obscure product differences. The workflow should produce a prioritized product issue report grouping identical or near-identical text and marking the groups that hide differences.
Topic
Product Data Quality and Audits
Target keyword
shopify duplicate product descriptions
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 detect repeated descriptions that obscure product differences.
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 description text per product with its product ID, the variant attributes that separate similar products, and the merchant similarity threshold for calling two texts the same]. Group the descriptions that meet the threshold, then test each group against the variant attributes and mark a group as hiding a difference only where its members differ in an attribute buyers choose on, such as material, size or finish.
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
Group the descriptions that meet the threshold, then test each group against the variant attributes and mark a group as hiding a difference only where its members differ in an attribute buyers choose on, such as material, size or finish.
03
Step 3
Deliver a prioritized product issue report listing each group with its member IDs, the shared passage, the differing attribute and the suggested rewrite, and confirm that every product in scope appears in exactly one group or as ungrouped.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why group by a threshold rather than exact matches only?
A changed word or a reordered sentence still reads as the same text to a buyer. Exact matching misses near-duplicates entirely, while a stated threshold catches them the same way across the whole catalog.
Which differences make a shared description a real problem?
Differences buyers choose on, such as material, size, fit or finish. Sharing text across products that differ only in an internal code or a packing quantity costs the buyer nothing and needs no rewrite.
Should every group found be rewritten?
Only groups where a real difference is hidden. Rewriting text shared by genuinely identical products adds inconsistency and more copy to maintain, without helping anyone decide between two listings.
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.
Find variants that lack the correct product image
Diagnose incorrect or inconsistent displayed product prices
Assess listing completeness using explicit review criteria
Identify missing or invalid variant prices
Design recurring audits for product data quality
Summarize catalog quality issues by product and severity
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.