01
Step 1
Collect the structured source rows, the mapping onto the product schema, the variant structure each row implies, the identifiers already assigned in the catalog, and the handle or SKU convention the merchant uses as the matching key.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Create draft product records from structured source information
New products arrive in a structured list, but some identifiers already sit in the catalogue and an unchecked import duplicates them. In this case, the immediate task is to create draft product records from structured source information. The workflow should produce a validated import draft with a row-level exception list, checked against the merchant's data.
Topic
Product Creation and Import
Target keyword
automatically create shopify products
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 draft product records from structured source information.
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 structured source rows, the field mapping onto the product schema, the implied variant structure, catalog identifiers already assigned, and the handle or SKU convention used as the matching key].
Build one draft record per source row after checking its key against the identifiers already assigned so an existing product updates instead of being duplicated, resolving rows that repeat one key inside the source against each other, and flagging rows whose parent product is absent, whose option values repeat, or whose required fields are empty.
Return a validated import draft with a row-level exception list 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
Build one draft record per source row after checking its key against the identifiers already assigned so an existing product updates instead of being duplicated, resolving rows that repeat one key inside the source against each other, and flagging rows whose parent product is absent, whose option values repeat, or whose required fields are empty.
03
Step 3
Deliver the records unpublished as drafts together with a row-level exception list naming the row, the field involved, whether the row was created or skipped and why, then reconcile created, skipped and rejected rows against the source row count and confirm no identifier appears twice in the output.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How is an existing product recognized?
Through the stable identifier the source supplies, compared against identifiers already assigned. Matching on title instead produces near-duplicates, because spelling and punctuation drift between feeds; rows carrying no usable key are not rescued by a name search either, they are listed unresolved for the merchant to place deliberately.
Do created records publish themselves?
No, they stay drafts until the mapping and variant structure have been reviewed, since a published listing is immediately visible to buyers. The review checks options, prices and images are present and sensible, and a draft corrected at this stage costs nothing, whereas fixing it later means editing live merchandising.
What happens to rows with empty required fields?
The row still becomes a draft for the fields it does support, and the missing ones are named in the exception list with the field involved. Nothing is invented to fill them, because a plausible placeholder is far harder to find and remove later than a blank noted at review time.
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.
Convert supplier records into Shopify product drafts
Prepare a validated batch of product listings for upload
Prepare a repeatable product import workflow
Prepare a product CSV with consistent identifiers and fields
Convert an Excel product list into a validated import draft
Extract supported product facts from supplied product URLs
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.