Ciwi
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant

Identify discrepancies in inventory records

A period close reveals gaps between book stock and counted stock, but nobody has traced them to their cause. In this case, the immediate task is to identify discrepancies in inventory records. The workflow should produce an inventory reconciliation and proposed correction file reconstructed from the merchant's own movement records.

Topic
Inventory Synchronization and Accuracy
Target keyword
shopify inventory discrepancy report
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 identify discrepancies in inventory 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: [book stock per SKU and location, movement history for the period, physical count results with their count date, and the cut-off time separating movements inside and after the period]. Restate both sides to the same cut-off by adding to the counted figure the movements recorded between the count date and that cut-off, then classify every remaining difference by cause, whether timing, damage, an unlogged movement or a unit-of-measure error, and total the quantity that stays unexplained.
Return an inventory reconciliation and proposed correction file 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.
Use in Spark
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.

01

Step 1

Collect the book stock per SKU and location, the movement history covering the period, the physical count results with their count date, and the cut-off time separating movements inside the period from those after it.

02

Step 2

Restate both sides to the same cut-off by adding to the counted figure the movements recorded between the count date and that cut-off, then classify every remaining difference by cause, whether timing, damage, an unlogged movement or a unit-of-measure error, and total the quantity that stays unexplained.

03

Step 3

Deliver an inventory reconciliation with one row per difference carrying both compared quantities, their timestamps and sources, the assigned cause and the proposed correction, add a summary line for reconciled items, and verify that explained plus unexplained differences equal the opening 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 the count before comparing?

A count taken before the cut-off misses the movements that happened afterwards, so comparing raw figures reports differences that are only timing. Adding those movements to the counted side puts both figures at the same moment, and what remains is a genuine discrepancy rather than a calendar artefact.

How is a cause assigned to a difference?

Only when a record supports it, such as a movement after the cut-off, a damage write-off, an unlogged transfer or a unit-of-measure error, and that record is named on the row. A difference with no supporting record stays unexplained and is quantified separately rather than given a convenient cause.

Should items that matched appear in the report?

Only as a summary line and a count, because the detail belongs to the unresolved differences that still need investigation. Every listed difference, however, carries both quantities, their timestamps and their sources, so a reviewer can reproduce the gap without reopening the whole period.

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.

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.

Open Spark product pageBack to Spark scenario library