METHODOLOGY · 10 min read · 20 May 2026

The Shopify metafields that make AI agents recommend your products: a vertical-by-vertical guide

In the 8 signals article we explained that metafields are the highest-leverage signal in the rubric. The gap between "zero AI-relevant metafields" and "three vertical-relevant metafields" is the largest single jump in catalog AI-readiness. This article answers the obvious follow-up question: which metafields, for which vertical?

Why structured data beats prose for AI shopping agents

When ChatGPT, Claude, or Perplexity answer a buyer query, they have two ways to read your catalog:

  • Structured retrieval.The agent calls a function that returns product objects with named fields (title, price, material, ingredients, etc.). It reads the fields it knows about.
  • Unstructured retrieval.The agent reads the product description as prose, runs it through embeddings, retrieves what looks relevant.

Structured retrieval wins whenever it's available. The agent doesn't have to interpret your marketing copy; it just reads the field. material: "merino wool" tells the agent something definitive. The same fact written as "made with our buttery-soft signature wool blend" requires interpretation and is lossy.

This is why metafields are weighted so heavily in the rubric: they're the part of your catalog that's already in the shape agents prefer.

Honest disclaimer. We don't run merchant-controlled experiments measuring "products with metafield X get cited Y% more". We have no clean counterfactual without merchant cooperation. What follows are the keys our open-source rubric scores against, mapped to AI agent retrieval patterns we observe. Treat it as a checklist, not a yield prediction.

The three universal metafield slots

Across every vertical, the audit rewards three "slot" metafields plus a universal taxonomy field. The slot names vary per vertical; the function is the same.

SlotFunctionWhy agents care
Google Product CategoryMaps your product to Google's standard taxonomy (e.g. Apparel & Accessories > Clothing > Activewear).Most agents have this taxonomy memorized. Matching it cleanly slots your product into category-level queries.
Material bucketWhat the product is made of or contains. Fabric for apparel, key ingredients for beauty, allergens for food, build material for electronics.The factual marker AI agents most aggressively check. Buyer queries like "merino wool sweater" or "retinol serum" lean on this field.
Dimensions bucketSize, weight, volume, capacity, or whatever quantitative attribute defines the product's physical instance.Disambiguation. Two products with the same name and different sizes are different products. Agents can't recommend correctly without this.
Care / usage bucketHow to use, store, apply, or maintain the product. Activity for fitness gear, skin type for beauty, age range for baby, storage for food.Targeting. Lets agents match products to specific buyer contexts ("for sensitive skin", "for newborns", "for trail running").

For each vertical below, we name the canonical key, list the variants our open rubric accepts, and show a concrete value example. Pick one canonical key per slot per vertical and apply it consistently across your catalog. The rubric source for every regex below is commerce-agentic/agentic-catalog-scanner.

The 10 verticals

APPAREL

Apparel: fabric, sizing, care

The most-cited apparel queries on AI agents are material-led ("merino wool sweater", "100% cotton t-shirt", "recycled polyester jacket"). Get the material field set on every product or you're invisible to those queries.

Material slot
Canonical: custom.material  ·  Accepted variants: composition, fabric, fibers, content
Dimensions slot
Canonical: custom.size_guide  ·  Accepted: dimensions, chest, inseam, waist, sizing
Care slot
Canonical: custom.care_instructions  ·  Accepted: wash, laundry, cleaning
Example value (material): "100% merino wool, 220 gsm, woven in Italy"
BEAUTY · HIGHEST UPLIFT FOR THE VERTICAL

Beauty: key ingredient, skin type, volume

Beauty queries are aggressively ingredient-led ("retinol serum for sensitive skin", "niacinamide moisturizer", "vitamin C with SPF"). The dominant slot is key_ingredient. Agents won't surface your product for an ingredient query if it isn't named in a structured field. Description prose is not enough.

Material slot
Canonical: custom.key_ingredient  ·  Accepted: ingredient, active, formulation, fragrance, extract
Dimensions slot
Canonical: custom.volume  ·  Accepted: size, capacity, ml, oz, net_weight
Care slot
Canonical: custom.skin_type  ·  Accepted: application, routine, usage, step
Example value (key_ingredient): "Niacinamide 10%, Zinc 1%, paraben-free, non-comedogenic"
HOME & FURNITURE

Home: wood type, dimensions, room

Furniture queries are dimensional ("dining table for 6", "queen bed frame", "shelf for small spaces"). Material drives the second wave ("solid oak", "marble coffee table", "rattan armchair"). Both must be set as structured fields, not buried in copy.

Material slot
Canonical: custom.material  ·  Accepted: wood_type, finish, upholstery, fabric, composition
Dimensions slot
Canonical: custom.dimensions  ·  Accepted: height, width, depth, seating_capacity, weight
Care slot
Canonical: custom.room  ·  Accepted: care, maintenance, assembly, style
Example value (dimensions): "W 180 cm × D 90 cm × H 75 cm · seats 6 · 38 kg"
ELECTRONICS

Electronics: chassis, specs, compatibility

Electronics queries are spec-led ("USB-C laptop", "noise-cancelling headphones with 30h battery", "Matter-compatible smart bulb"). Compatibility is the highest-leverage slot here. Agents match products to ecosystems (iOS, HomeKit, Matter, etc.) directly from the field.

Material slot
Canonical: custom.build  ·  Accepted: material, housing, chassis, finish
Dimensions slot
Canonical: custom.screen_size  ·  Accepted: display_size, battery_capacity, storage, weight
Care slot
Canonical: custom.compatibility  ·  Accepted: os_version, model_number, connectivity, warranty
Example value (compatibility): "iOS 17+, Android 12+, Bluetooth 5.3, USB-C charging"
FITNESS

Fitness: material, weight, activity

Fitness gear is queried by activity ("yoga mat", "cycling shoes", "running shorts") then by attribute ("moisture-wicking", "non-slip", "ergonomic"). The activity field is your matching key into category queries.

Material slot
Canonical: custom.material  ·  Accepted: composition, fabric, content
Dimensions slot
Canonical: custom.weight  ·  Accepted: size, capacity, resistance, gender
Care slot
Canonical: custom.activity  ·  Accepted: sport, skill_level, usage
Example value (activity): "Hot yoga, pilates, vinyasa flow · intermediate to advanced"
FOOD & BEVERAGE

Food: ingredients, serving size, storage

Food queries are diet-led ("gluten-free granola", "high-protein vegan", "single-origin coffee under $20"). Ingredients and dietary attributes must be in a structured field. Agents won't infer "vegan" from a product photo.

Material slot
Canonical: custom.ingredients  ·  Accepted: ingredient, allergen, dietary, composition
Dimensions slot
Canonical: custom.serving_size  ·  Accepted: net_weight, volume, serving
Care slot
Canonical: custom.storage  ·  Accepted: shelf_life, prep, origin, brewing
Example value (ingredients): "Organic rolled oats, almonds, maple syrup. Gluten-free, vegan, non-GMO."
PETS

Pets: species, breed size, life stage

Pet queries are tightly scoped ("food for senior small-breed dogs", "cat toy for kittens", "orthopedic dog bed for large breeds"). Species and life-stage are the two most disambiguating slots. Without them your product matches no specific query.

Material slot
Canonical: custom.material  ·  Accepted: composition, ingredient, content
Dimensions slot
Canonical: custom.breed_size  ·  Accepted: size, weight, capacity
Care slot
Canonical: custom.species  ·  Accepted: life_stage, activity, training
Example value (species): "Dogs · senior life stage · small breed (under 10 kg)"
BABY & KIDS

Baby: material safety, age range, certifications

Baby product buyers query safety-first ("BPA-free pacifier", "GOTS-certified organic crib sheet", "newborn to 12 months"). Safety certifications and age range are the must-have slots. Buyers won't trust a recommendation without these as structured fields.

Material slot
Canonical: custom.safety_cert  ·  Accepted: material, composition, fabric, certification
Dimensions slot
Canonical: custom.age_range  ·  Accepted: age_group, size, weight, seat_weight
Care slot
Canonical: custom.milestone  ·  Accepted: care, wash, age
Example value (safety_cert): "CPSIA, ASTM F963, EN-71 certified · BPA-free, phthalate-free, GOTS organic cotton"
OUTDOOR

Outdoor: material, capacity, weather rating

Outdoor gear queries are condition-led ("3-season tent", "waterproof hiking boots", "ultralight backpack under 1 kg"). Weather and skill-level slots are how agents narrow from broad activity queries to specific products.

Material slot
Canonical: custom.material  ·  Accepted: composition, fabric, fill, insulation
Dimensions slot
Canonical: custom.capacity  ·  Accepted: weight, volume, load, temperature_rating
Care slot
Canonical: custom.weather_rating  ·  Accepted: activity, terrain, skill_level, season
Example value (weather_rating): "3-season · comfort to -5°C · DWR shell, taped seams"
GIFTS

Gifts: recipient, occasion, presentation

Gift queries are intent-driven ("birthday gift under $50 for coffee lovers", "anniversary gift for him", "Mother's Day gift sets"). Recipient and occasion slots are essentially gift-specific. None of the other verticals have them, but gifts cannot be discovered without them.

Material slot
Canonical: custom.material  ·  Accepted: composition, content, gift_packaging, presentation
Dimensions slot
Canonical: custom.price_tier  ·  Accepted: size, weight, capacity
Care slot
Canonical: custom.recipient  ·  Accepted: occasion, gift_message, personalization, engraving
Example value (recipient): "Coffee enthusiasts · birthday, housewarming · presentation gift box"

How to set these in Shopify (the 5-minute version)

If you've never touched metafields in Shopify, the path is:

  1. Shopify admin → Settings → Custom data → Products.
  2. Add definition. Pick a namespace (custom works for most stores). Pick a key (use the canonical one above for your vertical). Pick a type (text for ingredients/material, dimension for sizes, etc.).
  3. Save. The field now appears in the Metafields section of every product edit page.
  4. Fill it on every product. Use bulk edit or a CSV import for catalogs > 20 SKUs.
  5. Also set Google Product Category on each product (Products → bulk edit → Category). This is the standard taxonomy field, independent of your custom metafields but equally important.

Time investment: 30 minutes for the definitions + 1-3 hours of bulk-fill for a 100-SKU catalog. The hardest part is psychological: picking your three canonical slot names and committing to them.

What this article doesn't claim

To be explicit about what we don't have:

  • We don't have controlled A/B data showing "products with metafield X get cited Y% more". A real test would require merchant cooperation, holding all else equal, observing AI capture rates before and after, none of which is feasible at our scale yet.
  • We do have the rubric, which is open source and weighted based on what AI agents demonstrably parse from product feeds.
  • We do have the captures dataset, which lets us observe that AI agents heavily cite brands whose catalogs use structured fields. But this is a correlation, not a causal claim.

Treat the canonical keys above as a tested checklist, not a yield prediction.

Audit your metafields in 60 seconds

Free audit covers the public catalog signals. Install the Shopify app to audit (and bulk-set) your metafields too.

Run a free audit Install on Shopify
Score Guarantee: +10 pts in 30 days or full refund.