Ciwi
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant

Check supplied descriptions for unsupported copied passages

Descriptions on several listings read as copied from supplier or marketplace text, and the merchant cannot tell which are its own. In this case, the immediate task is to check supplied descriptions for unsupported copied passages. The workflow should produce a per-listing review list quoting each overlap, the matched source and the recommended action.

Topic
Product Data Quality and Audits
Target keyword
product description plagiarism checker
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 check supplied descriptions for unsupported copied passages.
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 descriptions under review with their listing IDs, the reference passages supplied as candidate sources with their origin, and the merchant rule for the shortest shared span worth reporting]. Quote each overlapping span side by side with the passage it matches, record where it starts and ends and how much surrounding context agrees, and set aside shared facts, measurements and boilerplate that any seller of the item would write.
Return a per-listing review list naming the matched source and recommended action 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.
Use in Spark
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.

01

Step 1

Take the descriptions under review with their listing IDs, the reference passages supplied as candidate sources together with their origin, and the merchant rule for the shortest shared span worth reporting.

02

Step 2

Quote each overlapping span side by side with the passage it matches, record where it starts and ends and how much surrounding context agrees, and set aside shared facts, measurements and boilerplate that any seller of the item would write.

03

Step 3

Deliver a per-listing review list naming the matched source, the quoted span and the recommended action, and state plainly which comparisons could not be made because no candidate sources were supplied.

FAQ

Common questions when running this scenario

Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.

What separates copied wording from unavoidable shared text?

Specifications, measurements and standard care instructions read alike from any seller and are not copying. Extended identical phrasing with no factual constraint behind it is, and it carries more weight the longer the shared span runs.

Can the review clear a description as original?

Only against the sources supplied. A clean result means no overlap was found inside that set, not that the text is original everywhere, so the report should name what was actually compared.

What action follows a flagged passage?

Record the overlap and let the merchant confirm the licence or rewrite the passage. Taking a listing down is a merchant decision, because the same text may be licensed or may have come from the merchant own supplier.

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.

Open Spark product pageBack to Spark scenario library