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

Convert an Excel product list into a validated import draft

The product list lives in a workbook with inconsistent headers, merged cells and blank rows. In this case, the immediate task is to convert an Excel product list into a validated import draft. The workflow should produce a validated import draft with a row-level exception list, with row totals reconciled against the merchant's own workbook.

Topic
Product Creation and Import
Target keyword
import products from excel to shopify
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 convert an Excel product list into a validated import draft.
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 workbook, the stated meaning of each sheet and column, the target field mapping, and the structural defects present including merged cells, blank rows, header variants and text-stored numbers]. Prepare the sheet by promoting a single header row, splitting merged cells so every cell in a row holds a value, setting aside rows carrying no product, and casting numbers, dates and booleans into the target formats, then map each surviving row onto the schema and record any row that cannot be placed without guessing its meaning.
Return a validated import draft with a row-level exception list 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 workbook, a stated reading of which sheet and column carries which meaning, the target field mapping, and the structural defects present such as merged cells, blank rows, header variants or numbers stored as text.

02

Step 2

Prepare the sheet by promoting a single header row, splitting merged cells so every cell in a row holds a value, setting aside rows carrying no product, and casting numbers, dates and booleans into the target formats, then map each surviving row onto the schema and record any row that cannot be placed without guessing its meaning.

03

Step 3

Deliver a validated import draft with a row-level exception list naming every dropped or unmapped row and the reason, then reconcile imported, dropped and exception rows against the original sheet count and confirm all of this was done on a copy so the merchant's workbook stays available for checking.

FAQ

Common questions when running this scenario

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

How are merged cells made safe to import?

They are unmerged and the value filled down into every covered cell before mapping, because a merged cell reads as populated for one row and empty for the others. Filling down assumes one value applies to each covered row, so products where that is doubtful are flagged rather than silently completed.

Why work on a copy of the workbook?

The original is the reference used to check the outcome and to answer supplier questions later. Editing it in place removes the only baseline for settling disputes about what was supplied, and leaves no way to re-run the import after the mapping changes.

How do you know no row vanished by accident?

By reconciling counts at the end: rows imported, rows dropped as empty and rows listed as exceptions must add up to the original sheet count. Any gap means a row disappeared without an entry in the exception list, which is exactly the silent loss this check exists to catch.

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