01
Step 1
Take the product facts and the campaign goal, the approved brand asset library with the licence or usage scope attached to each asset, the formats and aspect ratios each channel accepts, and any overlay text the merchant has approved.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Create social image concepts for product campaigns
A merchant has a campaign to run but no visuals yet, and anything published has to stay inside the approved brand assets. In this case, the immediate task is to create social image concepts for product campaigns. The workflow should produce a visual brief per concept naming subject, framing and overlay text taken only from supplied product details.
Topic
Social Media Content Creation
Target keyword
ecommerce social media image generator
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 create social image concepts for product campaigns.
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: [product facts and the campaign goal, the approved brand asset library with usage scope per asset, the formats and aspect ratios each channel accepts, and the merchant's approved overlay text]. Turn each concept into a visual brief naming the subject, the framing and crop for the target aspect ratio, the approved asset it draws on and the overlay text, keeping overlay wording to the claim the merchant supplied and to characters that stay legible at the size the channel renders, and rejecting any concept that needs an asset outside the approved library or a crop that cuts the product's identifying detail.
Return image concepts with matching asset briefs 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.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.
02
Step 2
Turn each concept into a visual brief naming the subject, the framing and crop for the target aspect ratio, the approved asset it draws on and the overlay text, keeping overlay wording to the claim the merchant supplied and to characters that stay legible at the size the channel renders, and rejecting any concept that needs an asset outside the approved library or a crop that cuts the product's identifying detail.
03
Step 3
Deliver one brief per concept with the subject, the framing, the asset reference, the overlay text and the target format, mark each brief with the assets it consumes so two posts do not run the same visual in one period, and flag any concept whose overlay states something absent from the supplied product facts.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Can existing product photography be reused as is?
Only within the licence or usage scope attached to that asset in the library, and only where the raw image suits the channel's aspect ratio, since catalog shots are often square or tall and need reframing for a vertical placement. Reuse outside the recorded scope is flagged rather than assumed.
How much text should sit on the image?
Only the claim the merchant supplied, and only as much as stays legible at the size the channel renders. Overlay text must never introduce a detail the product record lacks, because an image claim is harder to retract than a caption.
Should every concept carry a call to action?
Where the campaign goal depends on a click, yes, and then short enough to read at thumbnail size. Purely informational or brand-led concepts work better without one, and forcing a directive onto them adds clutter without producing a measurable action.
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.