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

Apply a consistent watermark to owned product images

The merchant's own product photos circulate without a mark, and each new image is watermarked by hand in a different corner. In this case, the immediate task is to apply a consistent watermark to owned product images. The workflow should produce marked files or a placement brief using one placement and scale across the set, noting covered detail.

Topic
Product Image Editing
Target keyword
shopify product image watermark app
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 apply a consistent watermark to owned product images.
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: [written image ownership confirmation, the watermark asset, stated placement and opacity rules, the output size classes in use, and untouched original files for rollback]. Apply one placement and scale rule per size class so the mark stays legible on thumbnails without dominating heroes, and flag every image where the mark overlaps product detail, edges or lettering as an exception rather than shipping it silently.
Return the marked files or a placement brief 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

Confirm in writing which images the merchant owns, then collect the watermark asset, the stated placement and opacity rules, the output size classes in use, and the untouched originals to serve as rollback copies.

02

Step 2

Apply one placement and scale rule per size class so the mark stays legible on thumbnails without dominating heroes, and flag every image where the mark overlaps product detail, edges or lettering as an exception rather than shipping it silently.

03

Step 3

Deliver the marked files with a per-image log naming placement, scale, opacity and any exception, then verify the delivered file count equals the owned input count and that every original remains unchanged for rollback.

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 ownership confirmed before watermarking?

By checking the files against the merchant's own records of sourced or shot photography and getting a written confirmation; marking third-party or licensed images asserts rights the store may not hold, so anything unconfirmed is held out of the batch until its provenance is settled.

What happens when the mark covers product detail?

The image is flagged as an exception with the covered area named, and an alternate placement from the stated rules is proposed; the mark is never quietly moved per image, because ad-hoc placement is exactly what broke consistency across the set in the first place.

How is the batch verified after watermarking?

Count the delivered files against the owned input list, confirm each carries the stated placement, scale and opacity for its size class, and check that every original is still intact so any distorted or covered image can be rolled back exactly.

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