The merchant wants photography concepts before committing to a shoot or generated frames, with the product staying recognisable. In this case, the immediate task is to prepare accurate AI product photography concepts. The workflow should produce a concept set stating camera angle, background and lighting per concept while holding the appearance fixed.
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 prepare accurate AI product photography concepts.
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 product's verified appearance record, reference photography, brand styling rules, required output sizes per placement, and the merchant's disclosure rules for generated visuals].
Draft one concept per placement stating camera angle, background and lighting, hold the recorded appearance fixed across every concept, and flag any scene that implies a feature, scale or use the specification does not support.
Return the concept set or generated frames 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.
Gather the product's verified appearance record covering colour, finish and markings, the reference photography that shows it, the brand styling rules, the required output sizes per placement, and the merchant's stated disclosure rules for generated visuals.
Draft one concept per placement stating camera angle, background and lighting, hold the recorded appearance fixed across every concept, and flag any scene that implies a feature, scale or use the specification does not support.
Deliver the concept set or generated frames with a per-concept comparison against the reference, recording every drift in colour, proportion or markings, and apply the stated disclosure labelling before anything is scheduled for use.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Each frame is compared with the reference photography on colour, proportion, finish and markings, and every difference is logged as drift; a frame only passes when the item is recognisable as the same product, since buyers treat the image as evidence of what will arrive.
The concept step cross-checks each scene against the verified appearance record and specification, so staging that suggests water resistance, scale or materials the product lacks is flagged and reworked before any frame is generated.
One per placement the merchant has stated, each tied to a named purpose and output size; producing extra unattached variants wastes generation effort and multiplies the drift that must later be checked against the reference.
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.