WatchGet your catalog ready for agentic BFCM: a fireside chat with SimplisticWatch free
Back to Blog
Shopify's developer docs: About metafields

Shopify Metafields for AI Shopping Agents: What to Fill In

•7 min read•40rty team

Shopify metafields are custom fields that hold the product facts your standard fields don't: material, dimensions, fit, care, compatibility. For AI shopping agents those facts are the comparison. A shopper asks for “a linen shirt in navy, size L”, and the agent can only match on what your product data states. The metafields that matter most are Shopify's category metafields, and the way to make sure AI channels see them is to put them where Shopify Catalog reads.

This guide covers what metafields are, which ones agents use, and how to fill them. Sources are linked inline and were checked on October 29, 2026.

What Metafields Are

Shopify's Help Center defines metafields as a way to extend its data model, such as products, customers and orders, with your own custom data. Its examples: care instructions for apparel, recommended age and hazards for toys, dimensions for furniture, and size charts. Each metafield can have a definition that sets its type and validation, so “12 in” and “twelve inches” don't end up side by side.

Category Metafields: The Ones to Start With

Shopify's category metafields map to categories in its Standard Product Taxonomy, where they are called product attributes. Shopify says they help make products more discoverable on your site, on marketplaces and on search engines. Set a product category and Shopify offers the attributes that belong to it. For Apparel & Accessories > Clothing > Clothing Tops > Shirts, those include size, neckline, sleeve length type, top length type, age group, fabric, target gender, clothing features and color.

This is why the product category matters so much. It decides which attributes your product can carry, and the attributes are what an agent filters on. Shopify notes one limit: you can't remap the product category for Shopify Catalog, so it has to be right in the product itself.

Do AI Agents Read Metafields?

Be precise here, because many guides aren't. Shopify's list of product details AI platforms consider names title, description, images, type, vendor, collections, tags, barcode and variants with option names. It doesn't list metafields. Two documented routes still carry metafield content into AI channels:

  • Catalog Mapping. Shopify's mapping page says you can change the source of the title and description Shopify Catalog sends, choosing a product field or a metafield, combining sources with your own text, or editing the value as Liquid. It doesn't change your online store. A description that appends “Material: 100% linen. Fit: relaxed.” from metafields puts those facts in a field every AI channel reads.
  • Your product page. Metafields connected to your theme show on the page, where crawlers such as OpenAI's OAI-SearchBot and Google can read them. Google's AI features guidance asks that structured data match the visible text, so facts should be on the page, not only in markup.

The Attributes Agents Compare

OpenAI's product feed spec is the clearest public list of the attributes a ChatGPT product listing can carry. Here they are next to where they usually live in Shopify:

AttributeWhere it lives in ShopifyOpenAI feed field
ColorCategory metafield: colorcolor
SizeCategory metafield: size; variant optionsize, variant_dict
MaterialCategory metafield: fabric (apparel), or a custom metafieldmaterial
Who it is forCategory metafields: target gender, age groupgender, age_group
DimensionsCustom metafield such as Dimensionsdimensions, length, width, height
WeightVariant weightweight
CategoryProduct category (Standard Product Taxonomy)product_category

These are also the facts shoppers catch AI getting wrong. In 40rty's survey of 1,614 US online shoppers, 16% said AI had got sizes or colors wrong and 15% said it had got features or specs wrong. Two in three AI shoppers had seen some wrong product information, and 65% of them walked away from the purchase.

How to Fill Them In

  • Set the product category first. The category decides which category metafields appear.
  • Fill category metafields before custom ones. They follow a shared taxonomy, so their values mean the same thing across stores.
  • Add custom metafields for what shoppers ask. Look at your support tickets and reviews. If people ask about compatibility, waterproofing or care, give each a field.
  • Use definitions with types. A typed, validated field keeps values consistent across products, which free text never does.
  • Work in bulk. Shopify documents editing metafields in bulk from the admin.
  • Map, then check. Use Catalog Mapping to pull key metafields into the title or description Catalog sends, then search your own products in Shopify's Agentic search preview.

Metafields are one layer of a wider job. For the full field list ChatGPT reads, see how to rank in ChatGPT; for where these products go, see Shopify Agentic Storefronts; for why this beats publishing an llms.txt file, see what AEO is.

A shopper reads your product photo. An agent reads your metafields. Fill in the ones it reads.

FAQ

What are Shopify metafields?

Shopify defines metafields as a way to extend its data model, for products, customers, orders and more, with your own custom data. Examples from Shopify's docs include care instructions, recommended age, dimensions and size charts on products.

What are Shopify category metafields?

Category metafields are product attributes that map to a category in Shopify's Standard Product Taxonomy. Shopify says they help make products more discoverable on your site, on marketplaces and on search engines. A shirt, for example, gets size, neckline, sleeve length type, fabric, target gender, age group and color.

Do AI shopping agents read Shopify metafields?

Shopify's list of product details AI platforms consider names title, description, images, type, vendor, collections, tags, barcode and variants; it doesn't list metafields. You can make metafield content reach AI channels through Shopify Catalog Mapping, which lets you build the title and description that Catalog sends from metafields, without changing your store.

Which metafields matter most for AI shopping?

The ones a shopper's prompt filters on: size, color, material, dimensions, who the product is for, and compatibility. OpenAI's product feed spec has fields for material, color, size, gender, age group, dimensions and weight, which is a good guide to what agents compare.

Can I edit metafields in bulk?

Yes. Shopify's Help Center documents editing metafields in bulk from the admin, and metafield definitions let you set a type and validation so values stay consistent across products.

Check Your Store

The free 40rty audit scores a storefront's agentic commerce readiness, with no install and no account. Agents and developers can call it at GET https://audit.40rty.ai/api/audit?domain=<store>.

AgentIQ by 40rty builds agent confidence in your product listings, so AI shopping agents rank, recommend and add them to cart. It optimizes product listing hierarchies, metafields and descriptions around the shopping prompts your products should win, and tracks where they rank in Shopify Catalog. Plans are Small $49 a month (50 products), Pro $149 (1,000), Grow $499 (10,000) and Autopilot $799 (unlimited), per the App Store listing. Cheaper apps cover parts of this; our comparison of Shopify AEO and GEO apps says which.

More from our backlog