See how AI reads a product in your catalog

The How AI sees this product panel answers “why does this product rank where it does?” by showing exactly what Layers indexed for a product, what it ignored and why, and how variants were treated. It reads from the state the indexing pipeline already persisted, so opening it doesn’t trigger new work or extra model calls.

​

When to use this

• A product isn’t ranking where you expect and you want to see what the index actually contains for it.
• You want to confirm a metafield, tag, or collection made it into the index after a Shopify edit.
• You need to check how a product with variants was split into indexed entries.
• You see something that looks wrong in the indexed content and want to send it to the review team.

​

Open the panel

1. In the dashboard, go to Catalog and open a product. See View product details.
2. In the sidebar, find the How AI sees this product card.
3. Review the freshness pill, signal counts, and one-line strategy summary.
4. Select See full breakdown to open the slide-over.

​

What the sidebar card shows

• Freshness pill — Whether the indexed content reflects the current product data.
  • Up to date — The indexed content matches the current product data.
  • Needs a refresh — The product has changed since it was last indexed.
  • Never indexed — Layers has not indexed this product yet.
• Signal counts — Tags, collections, and metafields shown as included of total. For example, 6 of 14 means six of the fourteen tags on the product made it into the index.
• Strategy summary — One line that says whether the product was indexed as a single entry or split into several entries by a variant option (for example, Indexed as 3 entries, split by Color).

If a product has never been indexed, the sidebar card still renders. The slide-over then explains there is nothing to show yet.

​

What the full breakdown shows

A bar at the top of the slide-over names the indexing strategy Layers chose for this product and explains what it means in one line. Select How this was chosen in that bar to jump to the Variant treatment tab, which shows all three strategies with the active one selected. Below the bar the slide-over has two panes.

​

What the AI reads (left pane)

This pane shows the indexed content verbatim. It is the same structured view the embedded document is built from. Fields include Title, Brand, Category, Attributes, Variant options, Variant metafields, and Description. The description is clamped to three lines with a Show more toggle when the text overflows. When the product is split into multiple indexed entries (for example, one per color), a selector at the top of this pane lets you pick which entry to view. Entries are grouped by the distinct value of the splitting dimension, not per variant. Variants that share the split value produce the same document and count as one entry.

​

Signals and variant treatment (right pane)

The right pane has two tabs. Signals lists what was included and what was ignored for Tags, Collections, and Metafields. Included values render as green pills. Ignored values render as dashed pills and are grouped by the reason they were dropped. There are three ignore reasons. Each maps to a distinct stage of the indexing pipeline:

• Not shopper-facing content — Dropped before the selector saw it. Common examples are metafield definitions your store excludes, values that are only Shopify IDs, and empty values.
• Consistently unhelpful across your catalog — The field kept getting judged unhelpful for other products in your catalog, so Layers stopped considering it.
• Judged not descriptive for shoppers — The value reached the descriptiveness model, or an overriding verdict said it wasn’t useful to shoppers.

Counts read included of total. The total includes the values dropped before the selector saw them, so it matches what you’d see for the product in Shopify. Variant treatment shows how Layers decided to index a product with variants. It has three parts:

• Indexing strategy — Three cards showing every strategy Layers can use, with the one Layers picked for this product selected. The cards are read-only. The strategies are:
  • One entry for the whole product — Variant options are left out. Use for options that don’t change what the product is, like size or chain length.
  • One entry, with option values listed — Still one entry, but the meaningful option values are listed on it so the product is findable by any of them.
  • One entry per variant — Each variant is indexed on its own, carrying the full product identity plus that variant’s value.
• Variant attributes or options in the index — When the strategy is One entry, options listed, this section lists the option and metafield names Layers pulled onto the single entry. When the strategy is One entry per variant, it lists the options Layers used to split the index. Green chips mean the value shapes the index; dashed chips mean it does not.
• What Layers indexes for this product — The list of indexed entries. Each entry carries its splitting-dimension value as its label (for per-variant) or the product title. Select an entry to load it in the left pane.

​

Flag for review

If something in the indexed content looks wrong, flag it from the panel. You can flag the whole product from the header or flag a single tag, collection, or metafield value from the Signals tab.

​

Flag the whole product

1. Open the slide-over via See full breakdown.
2. Select Flag for review in the header.
3. Pick a reason:
   • Text that should not be there
   • Something important was left out
   • Variants are handled wrong
   • Something else
4. Add an optional note (up to 2,000 characters).
5. Select Send to review.

​

Flag a specific value

1. Open the Signals tab in the right pane.
2. Hover the value you want to flag. Both included (green) and ignored (dashed) values have a flag icon.
3. Select the flag icon. The popover shows a chip with the exact contract and value you’re flagging.
4. Pick a reason, add an optional note, and select Send to review.

Flags are unique per product and user. Sending a second flag replaces the first. Select Undo in the popover to withdraw a flag.

​

What happens after you send a flag

The panel header shows a status pill:

• Under review — A Layers agent is looking at the flag. It reads what’s currently indexed, consults your store knowledge, and decides whether the value should be kept or dropped for this product. The panel updates live as the agent progresses.
• Reviewed — The agent finished. If it changed anything, the Signals tab reflects the new decision. If it decided the current index is correct, nothing changes and the flag stands as a record.

The agent may pin a value as descriptive or non-descriptive for the product’s field, so Layers treats the same value consistently on future indexing runs. When it does, it can also write or update a document in your store knowledge so the reasoning applies across the catalog.

​

Freshness and the sidebar counts

The freshness state and signal counts are derived from the recorded indexing state, not by re-running any selection. This means:

• Opening the panel is instant and doesn’t cost model or API calls.
• If you edit a product in Shopify, the freshness pill reads Needs a refresh until the product is re-indexed. Trigger a re-index with Manually resync a single product, or with Push to Index from the bulk actions in the catalog list.

​

Tips

• If a value you expect to see is missing, check the Signals tab first. It will either be in the ignored list with a reason, or missing from the total. Which one it is tells you whether the value exists on the product at all.
• Field labels in the left pane are shown exactly as the index labels them, including underscores. That is on purpose. It is the label the AI sees, not a prettified name.
• For a split-indexed product, use the entry selector in the left pane to compare what a shopper searching for one variant value sees versus another.

​

Next steps

• View product details
• Manually resync a single product
• Resync your full catalog
• Manage store knowledge