01
Step 1
Collect close reference shots of the specific detail, the verified specification wording that describes its material and construction, the stated output size, and the list of features that must not be altered in the close-up.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Create a visual brief highlighting real product details
Buyers keep asking about one construction detail that no photo in the gallery shows clearly. In this case, the immediate task is to create a visual brief highlighting real product details. The workflow should produce a visual brief or generated close-up describing the detail, material and surroundings only as the records state, noting what must not change.
Topic
Product Image Generation
Target keyword
product detail 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 a visual brief highlighting real product details.
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: [close reference shots of the detail, verified specification wording for material and construction, the stated output size, and the list of features that must not change].
Describe the detail, its material and its surroundings using only the specification's own wording, size the feature large enough to read at the stated output size without cropping its identifying context, and flag every ambiguity in the record for a merchant ruling instead of guessing.
Return the visual brief or a generated close-up 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
Describe the detail, its material and its surroundings using only the specification's own wording, size the feature large enough to read at the stated output size without cropping its identifying context, and flag every ambiguity in the record for a merchant ruling instead of guessing.
03
Step 3
Deliver the visual brief or generated close-up with a word-for-word check of every material and construction claim against the specification, record the gaps and unresolved ambiguities separately, and hold the asset out of the gallery until each one is settled.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why must materials use the specification's wording?
Because a visually plausible but unrecorded material misleads buyers about what arrives; the close-up is checked claim by claim against the verified specification, and anything the record does not state is flagged for a ruling rather than rendered as if confirmed.
How much context stays in a detail close-up?
Enough of the surrounding construction to identify where the detail sits on the product, since a tight crop of stitching or finish alone could belong to any item; the framing keeps the feature readable at the stated output size while its location stays recognisable.
What happens when the reference is ambiguous?
The ambiguity is written into the brief as an open question and escalated to the merchant, and the asset is held rather than generated on an assumption; fine features differ between products, so guessing produces a close-up of an item the store does not sell.
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.