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

Find repeated product images that need review

The media library grew through several catalog imports, so one file now sits under many products with no record of which repeats were deliberate. In this case, the immediate task is to find repeated product images that need review. The workflow should produce a duplicate list with the affected products and a correction priority.

Topic
Product Image Quality and Errors
Target keyword
shopify duplicate image finder
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 find repeated product images that need review.
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 media inventory with file identifiers or checksums, product and variant associations, filenames, and import history]. Group files with matching identifiers as exact duplicates and visually compare near-identical ones at full size, then classify each repeat as deliberate reuse for shared variants or bundles, or as a listing error, sending deliberate-looking cases for a merchant ruling.
Return a duplicate list with the affected products and a correction priority confirmed case by case 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

Pull the media inventory with file identifiers or checksums, the product and variant associations for each file, filenames, and any import history, so exact repeats can be separated from lookalikes before judgment.

02

Step 2

Group files with matching identifiers as exact duplicates and visually compare near-identical ones at full size, then classify each repeat as deliberate reuse for shared variants or bundles, or as a listing error, sending deliberate-looking cases for a merchant ruling.

03

Step 3

Deliver the duplicate list naming affected products with a correction priority that puts live listings losing distinct views first, then verify each group's membership against the inventory so no file is listed in two groups or missed.

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 exact and near duplicates told apart?

Exact duplicates share the same file identifier or checksum and need only grouping, while near-identical files are compared at full size because a colour or crop edit can change what the buyer sees; the two classes are handled separately so nothing is merged on filename alone.

Which repeats are treated as deliberate?

Those where the shared file sits across variants of one product or across a bundle's components, recorded as intentional reuse pending the merchant's confirmation; only after that ruling is a repeat either kept or queued for correction.

How is correction priority set?

Live listings whose gallery loses distinct views to a repeat rank first because buyers lose information they would otherwise use, followed by live listings with redundant extras, then hidden or draft records, so the fix list reflects buyer impact rather than file counts.

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