New banner ideas exist only as a verbal description, so every placement ends up improvised at a different size. In this case, the immediate task is to create banner concepts for defined store placements. The workflow should produce banner briefs and size variants with every dimension checked against the stated placements.
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 banner concepts for defined store placements.
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: [brand assets and logo clear-space rules, each placement's documented dimensions and aspect ratio, the required message and offer copy, and the theme's file format and weight limits]. Compose each placement around a single focal subject inside a safe area that survives every required crop, mark any variant where headline or offer text crosses that boundary, and rework it rather than scaling text down to fit.
Return banner briefs and size variants with every dimension checked against the stated merchant placements 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 brand assets and logo clear-space rules, every placement with its documented pixel dimensions and aspect ratio, the message and offer copy each placement must carry, and the file format and weight limits the theme documents for uploads.
Compose each placement around a single focal subject inside a safe area that survives every required crop, mark any variant where headline or offer text crosses that boundary, and rework it rather than scaling text down to fit.
Deliver one banner brief per placement with its size variants and file constraints, list every variant's dimensions beside the placement it serves, and check the variant count equals the placements the merchant approved before publishing.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Each placement is matched to the dimension set the theme documents for it, and a variant is issued only when that set is known; placements without recorded dimensions go on a separate list so nobody has to guess a size.
Produce two crops from the same source rather than one stretched file, because a single file forced into a different aspect ratio distorts the product and usually pushes the offer text out of the safe area.
Count the variants against the approved placement list, confirm each file meets the documented weight and format limits, and open the smallest variant to confirm the offer text is still readable.
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.