New image ads are needed, but the only assets on hand are existing product photography, the style guide and approved claims. In this case, the immediate task is to create ad image concepts with distinct message angles. The workflow should produce image briefs with headline, focal subject and caption, each matched against the product facts on record.
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 create ad image concepts with distinct message angles.
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 photography on file, the style guide, the approved claim list, the placement and aspect ratio required per channel, and the product facts behind those claims].
Build each concept on one visual message such as the outcome, a detail or the context of use, keeping the product identifiable and any overlay text legible at the intended size, and dropping any concept that needs a claim outside the approved list.
Return image briefs with headline, focal subject and caption, each checked against the supplied product facts 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 photography on file, the style guide, the approved claim list, the placement and aspect ratio each channel requires, and the product facts those claims depend on, marking any image whose subject is not the product actually being advertised.
Build each concept on one visual message such as the outcome, a detail or the context of use, keeping the product identifiable and any overlay text legible at the intended size, and dropping any concept that needs a claim outside the approved list.
Deliver one brief per concept with its headline, focal subject, caption, target placement and the product facts it relies on, then check every brief against the approved claim list and reconcile the number of briefs with the number of placements in scope.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
The headline, the focal subject, the caption, the target placement with its aspect ratio and the product fact the visual leans on, so a reviewer can judge the concept without guessing which product or claim it was built for.
Only where the aspect ratios match closely enough that the subject and text stay inside the frame; otherwise the concept needs its own composition, since a crop that removes the product or the headline leaves nothing to review.
Only what stays legible at the smallest placement in scope, and only where the approved claim list covers it, because text that reads on a wide placement often becomes unreadable once the same file is cropped narrower.
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.