01
Step 1
Collect the variant-level stock snapshots with each variant's SKU and inventory item identifier, the location split behind each quantity, the availability rules the merchant applies, and the movement history recorded per variant.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Reconcile inventory at the individual variant level
Parent-level stock totals look balanced while individual size and colour variants tell a different story. In this case, the immediate task is to reconcile inventory at the individual variant level. The workflow should produce the variant reconciliation and proposed corrections checked against the merchant's own variant snapshots.
Topic
Inventory Synchronization and Accuracy
Target keyword
shopify variant inventory management
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 reconcile inventory at the individual variant level.
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: [variant-level stock snapshots with SKU and inventory item identifiers, the location split behind each quantity, the merchant's availability rules, and movement history per variant]. Reconcile each variant's snapshot against the position rebuilt from its own movement history and the last confirmed count, split reserved from freely sellable units at variant level rather than at parent level, and flag as exceptions the variants whose rebuilt quantity disagrees with the snapshot and those hidden inside a parent total that looks balanced.
Return the variant reconciliation and proposed corrections, with totals verified against the supplied 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
Reconcile each variant's snapshot against the position rebuilt from its own movement history and the last confirmed count, split reserved from freely sellable units at variant level rather than at parent level, and flag as exceptions the variants whose rebuilt quantity disagrees with the snapshot and those hidden inside a parent total that looks balanced.
03
Step 3
Deliver the variant reconciliation with one row per variant carrying the snapshot quantity, the rebuilt quantity, the difference and the proposed correction, group the variants that share a component or a bundle, and verify that corrected variant quantities still sum to the parent total before publishing.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why not reconcile at the product level?
A parent total can look balanced while one size is empty and another is overstocked, and the store sells variants rather than totals. Reconciling variant by variant is also what makes the correction writable, since stock is held against the variant's own inventory item and not against the product.
How is a proposed correction evidenced?
Each row carries the snapshot quantity, the quantity rebuilt from movement history, the difference and the movements behind it, so a reviewer can retrace the gap. Corrections stay proposals until the movement history is confirmed, because writing a change first often creates a second mismatch.
What about variants sharing a component?
They are listed together, because correcting one variant can change what is really available to its siblings. The shared constraint is applied before any correction is proposed, and where component stock is itself uncertain the whole group is held rather than corrected piecemeal.
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.
Synchronize stock while preserving quantity definitions
Update inventory from a designated source of truth
Prepare stock quantity updates from a verified source
Allocate a defined stock pool across eligible variants
Investigate differences between stock and order movements
Align variant stock quantities across connected records
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.