MentionFlow AI
Open app
DocsShopping

Product attributes

How AI shopping answers describe your product, in their own words, next to the brands winning the most shelf space. Extraction is rolling out.

Product attributes reads how AI shopping answers describe products. It captures the words, specs, and ratings the answer text states. Then it lines your product up against the brands winning the most carousel slots.

Note

The extraction pass is rolling out. It is flag-gated and off on production today. The comparison view is live, and shows an honest "not enabled yet" state until extraction is on for your workspace. Nothing here is inferred. Attributes appear only when an answer literally states them.

What it does

Answer text often describes the products on a shelf: "lightweight aluminium frame", "weighs 289 g", "rated 4.5 out of 5". Product attributes captures those descriptions and sorts them into three kinds:

  • Characteristics: descriptive text properties like material, style, or fit.
  • Facts: checkable specs. Numbers with their stated unit (including price with its currency), and stated yes/no properties like "fully waterproof".
  • Ratings: ordinal scores the answers state with digits, such as 4.5/5, 9 out of 10, or 88%.

Your product then sits side by side with the brands that won the most carousel slots in your window. You see where the AI describes you differently from the leaders.

Who it's for

  • Product and merchandising teams who want to know how AI assistants describe their products versus competitors.
  • Content and PR teams looking for the specs and claims AI answers repeat. Those are worth reinforcing on your own pages and in your knowledge base.

Try it

  1. Open Shopping and go to a product detail page (/shopping/products/[id]) for a product that has appeared in at least one carousel. The section only shows for products the AI has actually placed.
  2. Find the section headed "How AI describes this product".
  3. Switch between the Characteristics, Facts, and Ratings views.
  4. Read the matrix. Attribute rows run down the side. Your product is the highlighted This product column. Top competitor brands sit beside it, each labelled with how many carousel slots that brand won in the window.
  5. Hover any value to see the verbatim quote it came from. Follow the link to the real answer receipt where one is still live.

What you see while extraction is rolling out

Most workspaces see one of these states instead of the matrix:

  • Not enabled yet: "Attribute extraction isn't enabled yet." Shopping answers are being collected, but the pass has not run for your workspace. Once it is on, every shopping answer is scanned for stated attributes, with the quote kept as evidence.
  • Window not processed yet: a window whose answers have not been through the pass shows "This window hasn't been processed yet."
  • Nothing to extract: if the carousels listed products without stating any attributes, you see "No stated attributes found." Nothing is invented to fill the table.

How it's computed

  • Only what the text states. Every candidate is re-checked against the answer text before it is stored. The evidence must be a verbatim quote. A paraphrase or synonym is rejected ("featherweight" does not ground "lightweight"). Numbers must carry their stated unit with no conversion ("0.6 lb" cannot ground "272 g"). Ratings must be written with digits. An empty result is a valid answer.
  • Sample sizes, always. Aggregates carry their denominator. A characteristic reads "8/12 descriptions", never a bare "67%". The denominator is the distinct answers describing that brand. The numerator is the answers stating that value.
  • No fake math across units. Facts are pooled only within one stated unit. The dominant unit's range is shown. Every other unit is listed as excluded, marked "— not pooled", rather than converted. A 9/10 rating is never rewritten as 4.5/5.
  • Missing is an em-dash. A cell with no data shows an em-dash whose tooltip says why.
  • The comparison columns are the top competitor brands by carousel-slot count in your window, with your product always first. It is a side-by-side view of what the answers say, not a claim that any attribute causes a win.
  • The rollout flag. Extraction is controlled by the ATTRIBUTE_EXTRACTION flag. It is off by default because it spends language-model tokens per shopping answer. The history backfill is dry-run unless explicitly told to apply.

Limits

  • Extraction is rolling out and off on production today.
  • Sources follow shopping's engine coverage. ChatGPT, Google AI Overviews, Google AI Mode, and Copilot collect today. See Engine coverage.
  • You only ever see your own brand's data. Competitor columns are drawn only from brands reachable through your own placements. There is no separate plan gate on the feature.

Related