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

Prepare a product CSV with consistent identifiers and fields

The CSV is assembled from several sources, and identifier columns, separators and value formats do not match across rows. In this case, the immediate task is to prepare a product CSV with consistent identifiers and fields. The workflow should produce a validated import draft with a row-level exception list, checked against the merchant's column schema.

Topic
Product Creation and Import
Target keyword
shopify csv product import
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 a product CSV with consistent identifiers and 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 assembled source data, the import column schema, the product identifier column, and the required delimiter, encoding and quoting used throughout the file]. Rebuild the file on that schema giving each product one handle repeated across all its variant rows, one option definition per column position, and consistent number, date and boolean formats on every row, flagging rows whose identifier is blank, whose handle differs in form between rows of the same product, or whose text carries a delimiter conflict or a character the chosen encoding will not round-trip.
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 assembled source data, the import column schema for the CSV, the column carrying the product identifier, and the delimiter, encoding and quoting the file must use uniformly throughout.

02

Step 2

Rebuild the file on that schema giving each product one handle repeated across all its variant rows, one option definition per column position, and consistent number, date and boolean formats on every row, flagging rows whose identifier is blank, whose handle differs in form between rows of the same product, or whose text carries a delimiter conflict or a character the chosen encoding will not round-trip.

03

Step 3

Deliver the rebuilt file with a row-level exception list naming the affected rows and the problem found, then check it against the supplied column schema for header names and order, reopen the exported file to confirm delimiters parse and characters survive, and reconcile its row count with the source.

FAQ

Common questions when running this scenario

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

Why repeat the handle on variant rows?

The handle is what groups rows into one product, so a blank or drifted handle either splits one product into two or attaches rows to the wrong parent. Every variant row repeats the same handle string exactly, including case, which is why the version already living in the catalog is copied rather than retyped.

How are delimiters inside descriptions handled?

Through consistent quoting, so the parser reads the description as a single field. Mixed quoting lets one stray comma inside a sentence shift every later column by a position, which surfaces downstream as prices landing in a SKU column rather than as an obvious failure at upload.

What catches encoding damage early?

Reopening the exported file as plain text and sampling rows holding accented characters, currency symbols or non-Latin scripts. Garbled characters at that point mean the file was written in one encoding and read in another, which is cheap to correct before upload and slow to trace afterwards.

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