---
title: "AI agents and jewellery and accessories stores"
source: "https://ottom.io/verticals/jewellery-and-accessories"
summary: "Jewellery is small-catalogue, high-consideration and heavily photographed, which is the combination that produces the most beautiful pages an agent can read least. Materials, sizes and hallmarks are what a shopper asks about, and on most stores they are in the photography and the prose rather than in anything structured."
---

# AI agents and jewellery and accessories stores

Jewellery is small-catalogue, high-consideration and heavily photographed, which is the combination that produces the most beautiful pages an agent can read least. Materials, sizes and hallmarks are what a shopper asks about, and on most stores they are in the photography and the prose rather than in anything structured.

## What makes this category harder

- Material and carat are the primary filters and are almost never structured data.
- Ring and chain sizing is a variant dimension often presented as a guide image.
- One-off and limited pieces make stock a per-item fact that pages state loosely.

## Where agents stop, and why here

- design-led pages routinely ship without product markup (https://ottom.io/learn/stalls/missing-schema-org)
- sizes exist as a guide rather than as selectable variants (https://ottom.io/learn/stalls/no-variant-data)
- single-piece stock is stated in prose rather than as a field (https://ottom.io/learn/stalls/missing-availability)

## Questions

### Our pieces are one-offs. Does structured data even apply?

It applies more, not less. A single-piece product is exactly the case where an agent needs to know availability before recommending it, and prose that says "one available" is not something it can rely on.