01
Step 1
Pull each variant's identifiers as they appear in the store, the warehouse tool and the movement log, the per-location quantities each system reports, the open reservations held, and the extraction timestamp of every record.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Align variant stock quantities across connected records
The same variant reports different quantities in the store, the warehouse tool and the latest movement log. In this case, the immediate task is to align variant stock quantities across connected records. The workflow should produce the reconciliation and correction file taken from those overlapping records.
Topic
Inventory Synchronization and Accuracy
Target keyword
shopify sync variant inventory
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 align variant stock quantities across connected records.
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: [each variant's identifiers in the store, warehouse tool and movement log, per-location quantities from each system, open reservations, and each record's extraction timestamp]. Restate every quantity at one common cut-off by replaying the movements recorded after each system's extraction time, then compare the restated figures and attribute each remaining difference to a named movement, reservation or missing record rather than to whichever number was seen last.
Return the reconciliation and correction file, then flag any SKU whose evidence is incomplete 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
Restate every quantity at one common cut-off by replaying the movements recorded after each system's extraction time, then compare the restated figures and attribute each remaining difference to a named movement, reservation or missing record rather than to whichever number was seen last.
03
Step 3
Deliver the reconciliation with one row per variant and location showing each system's restated quantity, the difference, the attributed cause and the proposed correction under the merchant's source-of-truth rule, and hold as unresolved every variant whose movement evidence does not cover the whole gap.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why restate quantities at one cut-off?
Two systems extracted at different moments legitimately report different numbers, so comparing raw figures produces differences that are only timing. Replaying movements up to a shared cut-off removes those, and whatever difference survives is a real sync problem worth correcting.
Which system's number gets corrected?
The one the merchant's source-of-truth rule places lower, applied the same way to every variant. The winning figure, the losing figure and the reason for rejecting it are all recorded, so the same disagreement is settled identically next time instead of being re-argued row by row.
What if the movements do not explain the gap?
The variant is held as unresolved and listed in the open-items section with the unexplained quantity rather than corrected to force a match. An unexplained difference usually means a missing reservation or an unlogged movement, and guessing a value hides the defect that produced it.
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.
Update inventory from a designated source of truth
Identify discrepancies in inventory records
Reconcile inventory at the individual variant level
Prepare stock quantity updates from a verified source
Allocate a defined stock pool across eligible variants
Investigate differences between stock and order movements
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.