Product catalog tagging

Fill in missing tags and filters on a product catalog from titles and descriptions.

Run this on your file Download the template CSV

Before you run it: Replace the audience and season options with the filters your store uses. You can edit every question in the runner.

Columns to upload

Name the columns in your CSV like this. Extra columns are fine: every column of the row is sent with the questions.

Column	What it holds
`title`	Product title
`product_type`	Product type
`description`	Product description

Questions

Each question adds a column to your file. The answer is one of the listed values, or Unsure when the model's confidence is below the cutoff: 70% for pick-one and scale questions, 80% for yes or no.

New column	Question	Possible answers
`audience`Pick one	Who is the product for?	women Made for women men Made for men kids Made for children everyone Unisex or not specific
`season`Pick one	Which season is the product mainly used or bought in?	warm weather Spring and summer, or used outdoors in warm weather cold weather Fall and winter, or keeps you warm all year No season
`giftable`Yes or no	Does the description present the product as a gift, or is it a gift set?	yes It mentions gifts or a gift box, or is a gift set no It does not
`description_quality`Scale	How complete is the description?	missing or one line some details materials, size and use all covered Lowest to highest

Example row

Column	Value
`title`	Linen Picnic Blanket, Olive
`product_type`	Home
`description`	Washed linen, 150 x 200 cm. Folds into its own strap. Arrives in a gift box.

Answers from a test run on this row

Column	Answer	Confidence
`audience`	everyone	100%
`season`	warm weather	91%
`giftable`	yes	91%
`description_quality`	materials, size and use all covered	92%

More ecommerce use cases

Use case	What it does	New columns
Product reviews	Find out what reviews say about each product and pick the ones you can quote on the product page.	`aspect` `sentiment` `defect` `quotable`
Return reasons	Code the free-text reasons on returns and find the ones better product pages could prevent.	`reason` `preventable` `warehouse_fault`
Order notes	Pull the order notes that need someone to act before the order ships.	`note_type` `needs_action` `date_given`
Competitor product matching	Check whether the competitor listings you matched to your products are the same item before you compare prices.	`match` `same_size` `bundle`
Product listing quality check	Audit product titles and descriptions for missing attributes and mismatches before a marketplace or Google Shopping feed goes live.	`title_complete` `category_fits` `promo_text` `description_matches`