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

Map supplier CSV fields to the intended product fields

Before any upload, the supplier's column names have to be reconciled with the store's fields, and several are ambiguous. In this case, the immediate task is to map supplier CSV fields to the intended product fields. The workflow should produce a mapping table for merchant approval, matched against the merchant's own conventions and sample rows.

Topic
Product Creation and Import
Target keyword
shopify product csv field mapping
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 map supplier CSV fields to the intended product fields.
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 supplier's column headers, sample rows covering every column, the destination product fields with their permitted values, and the store's existing fill conventions]. Match each source column to exactly one destination field by comparing its actual contents rather than its label, writing beside each pair the validation rule and one example value lifted from the supplier file, and marking ambiguous any column whose contents fit two destination fields, whose values fall outside the destination's permitted set, or whose units or formats disagree with the store convention.
Return a mapping table for merchant approval before any upload 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 supplier's column headers, sample rows covering every column, the destination product fields with their permitted values, and the fill conventions already used in the store.

02

Step 2

Match each source column to exactly one destination field by comparing its actual contents rather than its label, writing beside each pair the validation rule and one example value lifted from the supplier file, and marking ambiguous any column whose contents fit two destination fields, whose values fall outside the destination's permitted set, or whose units or formats disagree with the store convention.

03

Step 3

Deliver the mapping table for merchant approval before any upload, listing each source column with its destination field, rule, sample value and any transformation required such as unit restatement or value remapping, and prove it by running sample rows covering every mapped column and reviewing the draft products they produce.

FAQ

Common questions when running this scenario

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

How is the destination decided when labels mislead?

By reading the column's actual contents. A header called variant detail holding colour words belongs in the option field whatever it is named, while one calling itself colour may carry codes needing remapping. Labels are noted, contents decide, and every ambiguous column goes to the merchant rather than being fitted by guesswork.

What proves a mapping before the full upload?

A sample run across a few rows chosen to cover every mapped column, reviewed as draft products. A file that uploads without complaint proves only that nothing crashed, whereas drafts showing correct options, units and values are real evidence, which is why the samples travel with the approval request.

Should unused supplier columns be deleted?

Leave them out of the mapping but keep them in the source file, recording why each was excluded. Deleting columns destroys context a later debugging session needs, and an unused column today often turns out to be the only place some required detail was ever recorded.

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.