Ad copy review

Check a batch of ad headlines and descriptions for the claim they make, how specific they are, and wording ad platforms often reject.

Run this on your file Download the template CSV

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
`headline`	The ad headline
`description`	The ad description
`landing_page`	The URL the ad sends people to

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
`claim`Pick one	What is the main claim the ad makes?	price A price, discount or free offer product feature What the product is or does social proof Reviews, ratings, customer counts or awards urgency A deadline or limited stock none No clear claim
`specific`Scale	How specific is the ad copy?	vague, could describe any product names the product type names the product and a concrete fact about it Lowest to highest
`has_number`Yes or no	Does the headline or description contain a number: a price, percentage, count or time?	yes It contains a number no It contains no number
`unproven_superlative`Yes or no	Does the ad claim to be the best, #1, cheapest or top-rated without naming a source?	yes It uses a superlative with no source no It uses no superlative, or cites a source for it

Example row

Column	Value
`headline`	The Best Natural Wine Club
`description`	Six bottles a month from small growers. Free shipping on 12.
`landing_page`	https://example.com/pages/wine-club

Answers from a test run on this row

Column	Answer	Confidence
`claim`	product feature	83%
`specific`	names the product and a concrete fact about it	99%
`has_number`	yes	98%
`unproven_superlative`	yes	97%

More marketing use cases

Use case	What it does	New columns
Google Search Console queries	Sort the search queries that bring people to your site by intent, topic and buying stage, and flag pages that do not answer the query.	`intent` `branded` `topic` `buying_stage` `page_fits` `ai_answerable`
Google Ads search terms	Find the search terms that spend money without buying intent, so you can add them as negative keywords.	`relevance` `intent` `competitor` `add_negative`
Social media comments	Sort comments on your Instagram, Facebook or TikTok posts so the ones that need a reply get one first.	`type` `sentiment` `needs_reply`
Blog and content inventory	Label every page of a content audit by format and funnel stage, and flag dated titles on subjects that come back every year, so you can update them.	`format` `funnel_stage` `recurring` `dated_title`
Keyword research list	Decide which page type each keyword needs before you plan content.	`intent` `page_type` `local` `question`