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

Prepare stock quantity updates from a verified source

A count spreadsheet has to become an update file, and every unmatched row risks writing quantity to the wrong variant. In this case, the immediate task is to prepare stock quantity updates from a verified source. The workflow should produce an inventory reconciliation and proposed correction file checked against the merchant's export and mapping.

Topic
Inventory Synchronization and Accuracy
Target keyword
shopify bulk inventory update
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 prepare stock quantity updates from a verified source.
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 verified quantity export with its extraction timestamp, the identifier mapping to SKU, inventory item and location, the required update format and column order, and the current quantities to be overwritten]. Match each export row to exactly one variant and location, reject rows whose identifier is missing, duplicated or mapped to more than one target, and hold as a discrepancy rather than stage any row whose quantity would fall below zero or jump beyond the merchant's stated plausible range.
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

Take the verified quantity export with its extraction timestamp, the mapping from its identifiers to SKU, inventory item and location, the update format and column order required, and the current quantities the change would overwrite.

02

Step 2

Match each export row to exactly one variant and location, reject rows whose identifier is missing, duplicated or mapped to more than one target, and hold as a discrepancy rather than stage any row whose quantity would fall below zero or jump beyond the merchant's stated plausible range.

03

Step 3

Deliver an inventory reconciliation listing matched, rejected and held rows with the reason for each, add a staged correction file in the required format carrying current and proposed quantities for rollback, and verify that staged rows equal matched rows before anything is applied.

FAQ

Common questions when running this scenario

Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.

What makes an export safe to stage from?

A traceable extraction time, an identifier that maps to exactly one variant and location, and agreement with the merchant's source-of-truth rule. An export missing any of those is not staged at all, because the failure mode of a bulk write is putting a correct-looking quantity onto the wrong variant.

How are unmatched or duplicated rows handled?

They are rejected with the reason shown, never silently dropped and never guessed into place. A duplicated identifier is a stronger warning than a missing one, since it means two different quantities are competing for the same variant and one of them must be wrong.

Why keep the current quantity in the file?

So a staged batch can be reversed row by row without rebuilding it, and a reviewer can see the size of each jump before it is applied. The rollback value also makes it visible when a batch was written over a later and more recent count.

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