01
Step 1
Take the product identifiers, the option names and values the product declares, the existing variants with their option values, SKU mappings, prices and images, and the confirmed combination list for that product.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Add valid variants to an existing product structure
An existing product declares options that only partly reach the catalog, so some allowed combinations have no variant behind them. In this case, the immediate task is to add valid variants to an existing product structure. The workflow should produce a variant matrix and precise change list, checked row by row against the option and SKU mappings on file.
Topic
Variant Creation and Management
Target keyword
add variants to existing 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 add valid variants to an existing product structure.
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 product identifiers, the option names and values the product declares, the existing variants with their option values, SKU mappings, prices and images, and the confirmed combination list for that product].
Build the allowed combination matrix from the declared options, match it against the existing variants by full option value set rather than by SKU alone, and mark every cell as present, missing, duplicated or impossible, using the confirmed list to decide which of the missing ones may be added.
Return a variant matrix and precise change list, checking each new row against the supplied option and SKU records 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 the allowed combination matrix from the declared options, match it against the existing variants by full option value set rather than by SKU alone, and mark every cell as present, missing, duplicated or impossible, using the confirmed list to decide which of the missing ones may be added.
03
Step 3
Deliver a variant matrix and precise change list checked row by row against the option and SKU mappings on file, then confirm that no added row collides with an existing variant and that the previous state of each touched product is recorded so the addition can be reversed.
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 a missing variant identified?
By a full option value combination the product declares but has no variant behind it, not by a gap in the SKU sequence. Matching on SKU alone misses variants whose SKU was never assigned and invents gaps where none exist, so the matrix is keyed on the option values and the SKU is checked against them.
Should existing variants be edited in the same pass?
No. Rows that are wrong are flagged and left for a separate change, so this pass contains only additions and stays reversible. Editing and adding together makes it impossible to tell which action produced a mismatch, and a combined list cannot be rolled back without losing the additions as well.
Do images need assigning before publishing?
Where the merchant keeps an image per option value, a new variant without one is flagged rather than published, because showing the wrong image misrepresents the option the shopper chose. Where no mapping is on file, the gap is recorded as a caveat so the decision stays with the merchant.
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.
Create missing variants from valid option combinations
Build a valid color-and-size variant matrix
Prepare a variant import from CSV source records
Standardize the names and values of variant options
Reorder product variants for a clearer selection experience
Identify duplicate variants and propose a cleanup mapping
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.