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

Check product images against defined quality requirements

The merchant has written rules for how product shots should look, but nothing checks uploads against them before publishing. In this case, the immediate task is to check product images against defined quality requirements. The workflow should produce a per-image checklist recording which requirement each file fails.

Topic
Product Image Quality and Errors
Target keyword
shopify product image 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 product images against defined quality requirements.
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 merchant's stated size, clarity and presentation criteria per placement type, and the images to review grouped by placement]. Score each image against every stated criterion and record the specific failure — the dimension short of the rule, the blur, the crop — rather than an overall impression, marking partly passing images with the exact requirement they miss.
Return a per-image checklist with pass or fail reasons confirmed against those records 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

Collect the merchant's stated requirements for size, clarity and presentation as separate testable criteria per placement type, and gather the images to review grouped by the placement each one serves.

02

Step 2

Score each image against every stated criterion and record the specific failure — the dimension short of the rule, the blur, the crop — rather than an overall impression, marking partly passing images with the exact requirement they miss.

03

Step 3

Deliver the per-image checklist with pass and fail reasons per criterion, then verify that every reviewed image appears exactly once and that pass and fail counts sum to the reviewed total before the list is used to schedule fixes.

FAQ

Common questions when running this scenario

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

What makes a check objective?

Each requirement is written as a testable criterion before any image is scored, such as a stated minimum dimension or a stated clarity rule; an image then passes or fails that criterion on evidence, and a check run without stated criteria is recorded as opinion rather than a finding.

How are partly passing images handled?

The failed criterion and its evidence are recorded while passing criteria stand, so the operator can re-export or re-crop the file instead of replacing it wholesale; the checklist shows which requirement failed, not just a blanket fail.

Does placement change the standard?

Yes, the same file can pass as a thumbnail and fail as a hero because the stated criteria differ per placement type, so images are grouped and scored against the rules of the placement they actually serve.

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