Step 1
Collect the source images, the background specification to be applied, the lighting cues visible in the original shot and the store's image rules for background, crop and output.
Replacement backgrounds are dropped in without checking how the light falls, so products look detached from it. In this case, the immediate task is to replace product-image backgrounds consistently. The workflow should produce editing instructions or processed images, matching direction, shadow and reflection to the object and to the store's image rules.
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.
Act as a Shopify operations specialist.
Help me replace product-image backgrounds consistently.
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 source images, the background specification to be applied, lighting cues visible in the original shot, and the store's image rules for background, crop and output]. Place the new background so its key light, shadow direction and reflection strength agree with the object, and adjust the contact shadow and any color spill at the edges rather than dropping the product onto it unchanged.
Return editing instructions or processed images 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.Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
Collect the source images, the background specification to be applied, the lighting cues visible in the original shot and the store's image rules for background, crop and output.
Place the new background so its key light, shadow direction and reflection strength agree with the object, and adjust the contact shadow and any color spill at the edges rather than dropping the product onto it unchanged.
Deliver editing instructions or processed images with the background used, the shadow and reflection settings and the export values, then check each image against the store's image rules and list those failing.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Take it from the object's own shading and cast shadow rather than assuming a studio default, because the highlight side and shadow side in the image are the only evidence of where the light actually was.
Only to correct color spill from the previous background and never to change the product, because catalogue images are read as a record of the item and a shifted hue invites a mismatch claim.
Fix one background value, one shadow treatment and one export setting, then apply them unchanged to every image, because per-image adjustments are what make a grid look uneven.
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
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.