The Score in One Sentence
Copy Opt's new score answers one question: what share of your product's real shopper demand does your listing copy actually cover?
The word doing the work in that sentence is "demand." In the previous version of Copy Opt, demand meant one thing: the search queries shoppers type. The new score measures your copy against two kinds of demand at once. The queries shoppers type, and the intents behind them, meaning what the shopper is actually trying to accomplish. A listing can echo every top search term and still never say who the product is for, what situation it serves, or what it works with. Those unstated intents are demand your copy is leaving uncovered, and Amazon's own research says its ranking systems now look for them.
Query coverage tells you whether your copy matches what shoppers type. Intent coverage tells you whether it answers why they typed it. The new score considers both without reducing either to a keyword checklist.
What COSMO Actually Is (And Isn't)
In 2024, Amazon published a paper describing COSMO, its large-scale commonsense knowledge system for e-commerce ("COSMO: A Large-Scale E-commerce Common Sense Knowledge Generation and Serving System at Amazon," SIGMOD 2024). The motivating example in the paper is a shopper searching for "shoes for pregnant women." Nothing in a shoe listing says "pregnant." What the shopper needs is slip resistance, comfort, and easy on-off. Amazon's classic matching systems could not bridge that gap, because the connection is not in the words. It is in commonsense knowledge about why someone with that need buys that product.
COSMO closes the gap by mining those connections at scale: large language models generate candidate relationships from real search and purchase behavior, and human review plus critic models filter them into a knowledge graph that Amazon serves inside product search.
Two things are worth being precise about, because much of the seller commentary on COSMO gets them wrong:
- COSMO is an augmentation layer, not a new ranking engine. It feeds intent knowledge into the same retrieval and ranking pipeline Amazon has documented for years. There was no switch flipped from an old algorithm to a new one.
- The direction is real, though. Amazon is investing in understanding what shoppers are trying to accomplish, not just what they type. Listings that state use cases, audiences, and compatibility give both the knowledge layer and the shopper more to connect with.
Copy Opt's new scoring model takes the same step from the seller's side: it stops treating queries as the whole of demand and starts scoring the intents behind them as demand in their own right.
Where Query Coverage Falls Short
Here is the failure mode the old score could not see. Take a dog bed with strong query data. The copy mentions "orthopedic," "washable," and "large dog bed," so query relevance looks healthy. But look at what those queries are actually expressing:
A listing that says "orthopedic memory foam dog bed, machine-washable cover, 42 x 30 inches" matches the queries. But it never says for senior dogs, never says fits inside a 42-inch crate (dimensions are not the same claim as fit), and makes the shopper do the work of connecting foam density to an aging dog's joints. Those are pieces of demand the copy leaves on the table, and they are invisible to a score that only checks queries.
From Search Terms to Shopper Needs
Copy Opt starts with demand visible in your account, then organizes it around the questions a listing needs to answer. Search terms supply the shopper's language. The needs behind them reveal audience, use case, fit, compatibility, or another buying concern that may never appear word for word.
That distinction keeps the analysis grounded. A phrase such as "orthopedic memory foam" names a product feature, but it does not tell an older-dog owner what that feature will do. A useful recommendation connects that missing explanation to demand shoppers have already shown.
You can review the needs Copy Opt identifies, dismiss what does not apply, and add product knowledge the data cannot supply. Those choices stay with the product, so the analysis reflects your catalog instead of treating every plausible idea as fact.
How Coverage Is Evaluated
Copy Opt checks whether the listing makes each important shopper need clear. Exact phrasing may be enough in some cases. In others, the copy must explain what a feature does or state compatibility plainly. The goal is to catch the point where a shopper has to make an unsupported leap.
The result is a prioritized view of gaps tied to the demand behind them. Your team can inspect the evidence, reject a bad assumption, and decide which claims are both true and worth adding.
Every recommendation stays tied to underlying shopper demand and the specific place where the listing falls short. You can inspect that evidence without needing access to Copy Opt's proprietary scoring mechanics.
What the Score Means
The score turns that analysis into a consistent benchmark for the listing. It is not a keyword checklist or a grade on writing style. It summarizes whether important shopper questions are answered, so a small wording improvement does not crowd out a missing use case or compatibility claim.
How to Read Your Score
Start with gaps backed by the clearest shopper evidence. Some listings repeat search terms well but never say who the product is for or what situation it serves. Others provide materials and dimensions yet leave the reader to infer the benefit or fit.
Only add a claim if it is true for the product. The strongest recommendations are often direct sentences that clarify an existing fact, not wholesale rewrites or extra keyword repetition.
Grading the Score Against Reality
A score you cannot audit is a vibe. Copy Opt keeps recommendations tied to demand you can inspect, and its benchmarks are checked against patterns across live catalogs rather than invented in isolation.
Published changes can also be compared with later marketplace performance. We treat those comparisons as observational, not a controlled experiment: ad spend, price, seasonality, and competitors can move results, so the data provides context rather than proof of causation.
- Amazon's COSMO system (published SIGMOD 2024) adds commonsense intent understanding to product search. It augments the existing ranking pipeline rather than replacing it.
- Copy Opt evaluates both the search language shoppers use and the needs behind it, without treating listing quality as a keyword checklist.
- Your team can inspect the demand behind a recommendation, dismiss ideas that do not fit, and add product knowledge the data cannot supply.
- Benchmarks are checked against live catalog patterns, while post-publish performance is treated as observational evidence rather than proof of causation.