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

Normalize inconsistent catalog data formats

A catalog export mixes casing, unit spellings and separators from record to record, which breaks filters and downstream feeds. In this case, the immediate task is to normalize inconsistent catalog data formats. The workflow should produce an enriched product data draft holding one format per field, plus the records too irregular to normalize safely.

Topic
Product Data Enrichment
Target keyword
standardize product data
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 normalize inconsistent catalog data formats.
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 catalog export, the per-field format rules, the fields feeding filters and downstream feeds, and the variation inventory across current records]. Normalize casing, whitespace, unit spelling, separators and the representation of boolean and date values field by field, leaving untouched and separately listed any value that will not parse under the rule, and recording the before and after of every change so the merchant can review what moved.
Return an enriched product data draft with unresolved fields 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 catalog export, the format rule each field must satisfy, the list of fields feeding filters, comparisons and downstream feeds, and an inventory of the variations actually present in those fields today.

02

Step 2

Normalize casing, whitespace, unit spelling, separators and the representation of boolean and date values field by field, leaving untouched and separately listed any value that will not parse under the rule, and recording the before and after of every change so the merchant can review what moved.

03

Step 3

Deliver an enriched draft holding exactly one format per field plus a list of records too irregular to normalize safely with their original values intact, then re-read the merchant's original export to reconcile row and column counts and sample-check that no normalized value changed its meaning.

FAQ

Common questions when running this scenario

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

Which fields are normalized first?

Those feeding filters, comparison tables and downstream feeds, because inconsistent writing there breaks customer-facing selection and integrations at the same time. Purely descriptive prose can wait, since starting there spends effort where the catalog already tolerates variety without complaint.

How do you know meaning survived a rewrite?

Every change is recorded as before and after, and a sample across each field is reviewed with the original alongside it. Consistent formatting should never alter what a value asserts, so any row where meaning shifts is reverted and listed rather than accepted for the sake of uniformity.

What happens to values no rule fits?

They are left exactly as found and carried into a separate list naming the field and why it failed to parse. Forcing them through a rule risks turning an unusual but correct value into a plausible wrong one, which is considerably harder to detect later than a flagged outlier.

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