The only material on hand is product photography and short notes, so anything not visible has no support. In this case, the immediate task is to draft product listings from visible image evidence. The workflow should produce an import draft with a row-level exception list naming each unresolved field, leaving materials for supplier confirmation.
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 draft product listings from visible image evidence.
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 source images and their accompanying notes, each image's angle and scale cues, the target listing schema, and existing catalog identifiers for the same items]. Record only attributes the images plainly show — form, colour, visible components, printed labels and any measurement readable against a stated scale — leaving material composition, certifications, exact dimensions, care instructions and identifiers as unresolved fields, and flagging images too cropped, reflective or low in detail to support even those readings.
Return an import draft with a row-level exception list naming each unresolved field 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 source images, any notes supplied with them, what each image actually shows including its angle and whether a scale cue is visible, the target listing schema, and the catalog identifiers of these same items where they already exist.
Record only attributes the images plainly show — form, colour, visible components, printed labels and any measurement readable against a stated scale — leaving material composition, certifications, exact dimensions, care instructions and identifiers as unresolved fields, and flagging images too cropped, reflective or low in detail to support even those readings.
Deliver a listing draft with a row-level exception list naming per image every unresolved field and who can confirm it, then check the visible readings against the merchant's own photography and existing catalog entries and note which facts rest on printed text rather than on something the supplier documented.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Treat it as a lead rather than a verified fact. Packaging claims are written for the shelf and can predate a reformulation or a regulatory change, so anything taken from printed text is marked as needing supplier confirmation, while purely visual attributes carry no such caveat.
Appearance and little beyond it. One shot rarely establishes dimensions, materials, identifiers or compliance fields, so those stay unresolved until another source supplies them; several angles plus a visible scale raise what can be stated, but never enough to complete a listing alone.
Describe it in the store's own colour vocabulary, using the nearest existing product term, and note where lighting or background makes the reading doubtful. Inventing a distinctive shade commits the listing to a claim no buyer could check, so uncertain rows are flagged rather than named.
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.