Product Schema for AI Search — Shopify JSON-LD Implementation Guide

Only 12% of Shopify merchants have shipped comprehensive Product schema markup - the single most actionable step for AI discoverability (Metricus, 2026). Schema-compliant pages get cited 3.1x more often in Google AI Overviews. So this guide is the specific version: exactly which fields ChatGPT Shopping, Perplexity, and AI Overviews pull - and how to ship them on Shopify without an app if you want.

Why AI needs Product schema, not just HTML

Schema is one of six signals on the AI-ready product page checklist, and it's the one I'd fix first. AI retrieval systems read structured data before they parse HTML. When ChatGPT Shopping decides which products to recommend, it reads the JSON-LD first - name, price, availability, rating, brand. No schema and the AI is left guessing: scraping price out of CSS-styled text, inferring availability from phrases like "in stock" or "sold out." Slower, less reliable, and frequently skipped entirely. You're making it do work it would rather skip - so it skips you.

Required fields (2026 update)

Google raised the bar on e-commerce Product schema in 2026. Minimum fields for full eligibility:

• name - product name (plain text)
• image - at least one product image URL
• description - plain text, 50+ characters
• brand - Brand entity with name
• sku or mpn or gtin - a unique product identifier
• offers - Offer entity with price, priceCurrency, availability, url
• aggregateRating - if reviews exist (ratingValue, reviewCount)

Highly recommended fields (2026)

Google now strongly recommends these for merchant-eligible rich results - "recommended" here means "you lose results without them":

• hasMerchantReturnPolicy - explicit return window, fees, country
• shippingDetails - estimated shipping cost, delivery time, destination
• gtin / gtin8 / gtin13 / gtin14 - global identifiers for product verification
• energyEfficiencyCategory - for electronics (EU markets)

Complete Product schema example

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Product",
  "name": "CloudRunner Pro Running Shoe",
  "image": [
    "https://yourstore.com/products/cloudrunner-pro-1.jpg",
    "https://yourstore.com/products/cloudrunner-pro-2.jpg"
  ],
  "description": "Neutral daily training shoe for 30-50 mile/week runners. CloudTec foam midsole with 23% more energy return than previous model.",
  "brand": {
    "@type": "Brand",
    "name": "CloudRunner"
  },
  "sku": "CR-PRO-2026",
  "gtin13": "0123456789012",
  "offers": {
    "@type": "Offer",
    "url": "https://yourstore.com/products/cloudrunner-pro",
    "priceCurrency": "USD",
    "price": "159.99",
    "priceValidUntil": "2026-12-31",
    "availability": "https://schema.org/InStock",
    "itemCondition": "https://schema.org/NewCondition",
    "shippingDetails": {
      "@type": "OfferShippingDetails",
      "shippingRate": {
        "@type": "MonetaryAmount",
        "value": "0",
        "currency": "USD"
      },
      "shippingDestination": {
        "@type": "DefinedRegion",
        "addressCountry": "US"
      },
      "deliveryTime": {
        "@type": "ShippingDeliveryTime",
        "handlingTime": {"@type": "QuantitativeValue", "minValue": 0, "maxValue": 1, "unitCode": "DAY"},
        "transitTime": {"@type": "QuantitativeValue", "minValue": 2, "maxValue": 5, "unitCode": "DAY"}
      }
    },
    "hasMerchantReturnPolicy": {
      "@type": "MerchantReturnPolicy",
      "applicableCountry": "US",
      "returnPolicyCategory": "https://schema.org/MerchantReturnFiniteReturnWindow",
      "merchantReturnDays": 60,
      "returnMethod": "https://schema.org/ReturnByMail",
      "returnFees": "https://schema.org/FreeReturn"
    }
  },
  "aggregateRating": {
    "@type": "AggregateRating",
    "ratingValue": "4.7",
    "reviewCount": "342"
  }
}
</script>

Shopify implementation

Shopify ships basic Product schema in most themes, but "basic" usually means "incomplete," and incomplete is the problem this whole post is about. Two ways to fix it:

Option 1: edit theme.liquid (what I'd do)

Add a custom Product schema snippet in sections/product-template.liquid or your theme's equivalent, after the existing structured data, and pull real product data with Liquid variables:

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Product",
  "name": {{ product.title | json }},
  "image": {{ product.images | map: 'src' | json }},
  "description": {{ product.description | strip_html | json }},
  "sku": {{ product.selected_or_first_available_variant.sku | json }},
  "brand": {
    "@type": "Brand",
    "name": {{ product.vendor | json }}
  },
  "offers": {
    "@type": "Offer",
    "url": "https://{{ shop.domain }}{{ product.url }}",
    "priceCurrency": {{ shop.currency | json }},
    "price": "{{ product.selected_or_first_available_variant.price | money_without_currency | strip }}",
    "availability": "{% if product.available %}https://schema.org/InStock{% else %}https://schema.org/OutOfStock{% endif %}"
  }
}
</script>

Option 2: use an app

Apps like Schema Plus, JSON-LD for SEO, or Schema App Total Schema Markup handle this automatically. The one thing to actually check before you install: that it supports the 2026 Google updates (merchant return policy, shipping details, GTIN). An app stuck on the old spec just automates the gap.

Validation steps

1. Test structure: Schema.org Validator - confirms syntactic validity
2. Test eligibility: Google Rich Results Test - eligibility for Google rich results and AI Overviews
3. Test the live URL: run the tests on your actual product URL, not just the generated JSON - that's how you catch the rendering issues that look fine on paper

What AI engines actually extract

When I dug into our ChatGPT Shopping, Perplexity, and Google AI Overviews citation data, the thing that jumped out is they don't all read the same fields:

• ChatGPT Shopping: prioritizes name, brand, offers.price, aggregateRating, image
• Perplexity: leans hard on description for context, plus all offer fields
• Google AI Overviews: requires hasMerchantReturnPolicy and shippingDetails for merchant rich results

GEOlikeaPro's AI Readiness audit checks your Product schema against every 2026 requirement and tells you exactly which fields are missing. The Crawler View shows what ChatGPT Shopping actually extracts from your store. Sign up free to audit your products.