How to Make Your Fashion PDP Readable by AI Shopping Agents — The Agentic Commerce Checklist (2026)

Why this matters now

Shopping-related searches on generative AI platforms grew 4,700% between July 2024 and July 2025 (BoF × McKinsey, State of Fashion 2026, p.38). ChatGPT already drives 16% of Zara's inbound referral traffic and 8% of H&M's (State of Fashion 2026, p.38, citing SimilarWeb). OpenAI has struck deals with both Shopify and Etsy to enable direct purchasing through ChatGPT (State of Fashion 2026, p.40, p.44). Amazon has launched "Buy for Me". Google and Perplexity both have purchase agents in market.

The McKinsey and Business of Fashion State of Fashion 2026 report makes the commercial priority explicit: brands should "optimise for AI discoverability by overhauling product content and digital infrastructure so AI agents can readily access and read it" (p.37, p.43). It adds that "semantically rich data and API-accessible content will be critical to success" (p.37). And it quotes Marc Bain on the stakes: brands not appearing in an AI agent's consideration set "may as well be invisible" (p.44).

GEO — Generative Engine Optimisation — is what McKinsey calls "the new SEO" and a "critical counterpart to SEO" (State of Fashion 2026, p.7, p.39). For fashion brands, GEO is not a future-state project. It is a current competitive decision.

The checklist below covers the seven areas that determine whether an AI agent can read, evaluate, and recommend your fashion products. For each, we note what the gap typically looks like on a Shopify store and what to do. Agent and API integrations are discussed per store: confirm availability before relying on one. See Rendered Fits product facts.

1. Structured product data — write for machines, not just shoppers

AI agents parse raw text. Vague copy — "a beautiful floaty dress in our signature silk" — cannot be matched against a shopper's requirements. Concrete attributes can.

For every product page, ensure:

Product title includes garment type, brand, and at least one key attribute (material or fit) — not just a style name.
Description states: material composition (percentage breakdowns where relevant), care instructions, fit type (oversized/relaxed/slim/structured), body-length reference (mini/midi/maxi, or cm from waist), and country of origin if premium-relevant.
Size options are labelled in full (Small, not S; UK 10, not 10) and include a prose size guide on the PDP itself — not a separate linked PDF.
Dimensions table (chest, waist, hip, length) is present per size, in centimetres, as on-page text (not only an image).

Common gap on Shopify

Size guides published as images or PDFs are invisible to AI agents. Dimensions must be in crawlable HTML text — a simple table is sufficient.

2. Product JSON-LD — Schema.org markup on every PDP

JSON-LD is the format AI crawlers and shopping agents read most reliably. Shopify themes often include a partial Product schema block by default; most are missing fields that matter to agents.

Minimum required fields for a Schema.org/Product block:

name, brand, description
image (array — include at least 3 angles)
sku (per variant)
offers: price, priceCurrency, availability, url

Recommended additions that meaningfully improve agent comprehension:

material, color, size
aggregateRating (with ratingCount)
review (array, with reviewBody and author)
sizeSpecification (Schema.org/SizeSpecification)

Audit your current markup using Google's Rich Results Test. Missing required fields generate errors; missing recommended fields generate warnings. Errors suppress structured-result eligibility. Warnings reduce agent comprehension.

Common gap on Shopify

Default Shopify themes emit a Product schema block with name and offers, but rarely include aggregateRating, review, or sizeSpecification. These are exactly the fields AI agents use to distinguish products in the same category.

3. Page metadata — title, description, and Open Graph

Perplexity, ChatGPT Browse, Google AI Mode, and similar systems read page metadata as the authoritative one-line summary of your page. They surface this directly in citations and shopping results.

Page title should lead with the product name and brand. Avoid leading with your site name.
Meta description should state the key purchase-decision attributes in one sentence: material, fit, use-case, and price point if distinctive. This is what an AI answer engine surfaces in a citation.
og:title and og:description should match or closely mirror the title and meta description. These are read by social crawlers and AI systems parsing Open Graph data.
og:image should be a clean, high-resolution product shot — preferably on a person, not a hanger. AI systems use images as a quality signal for the underlying product.

Shopify's default meta templates use the product title as the page title and a truncated description as the meta description. Both are usually adequate, but most themes do not populate og:image correctly (they use the first product image at full-size rather than a cropped 1200×630 social asset). This is a minor fix with a meaningful impact on how the page appears when cited.

4. Social proof and reviews — structured and on-page

Approximately 80% of sources AI systems draw on are third-party content — reviews, editorial, affiliate — rather than brand-owned pages (State of Fashion 2026, p.41). This has two implications: first, your on-site reviews need structured markup so they are readable as authoritative signals; second, off-site reviews on platforms AI already trusts amplify your visibility beyond your domain.

For on-site reviews:

Add Schema.org/Review and Schema.org/AggregateRating to your Product JSON-LD block.
Prioritise displaying reviews that use natural purchase-language: "true to size", "runs small in the shoulders", "surprisingly warm for the weight" — the language an AI agent will match against a shopper's stated requirements.
Include reviewer attributes where consented (height, usual size, body type): structured agent-readable fit testimonials are more valuable than general praise.

For off-site reviews:

The Shopify App Store (if you are an app) and Google Business reviews are indexed and cited by AI systems.
Trustpilot, Yotpo published pages, and editorial mentions in fashion media (Vogue, WWD, Drapers) carry disproportionate weight as third-party validation sources.
AI answer engines use grounding queries to validate brands they surface — searches for "[brand] review", "[brand] returns policy", "is [brand] legit". Having rich, independently indexed content at these query shapes is what survives the validation pass.

5. Fit and sizing information — the critical gap for fashion

Fit and sizing are the decisive purchase-confidence factors in fashion, and the hardest to make readable. A size guide written in a table is better than a PDF, and a size guide in JSON-LD is better still. A direct endpoint an agent could call is more machine-useful again, but whether one exists for your store is a per-store question, not something to assume.

The McKinsey exec priority is explicit: "semantically rich data and API-accessible content will be critical" (State of Fashion 2026, p.37). In fashion, fit is the semantically rich data. Start with what you control, then decide with your vendors what more is worth building.

Three approaches, starting with the ones you control:

Option A — Structured text on the PDP (minimum viable)

Include a size guide as an HTML table on the PDP with measurements in centimetres per size, and a short fit note per product (true to size, runs small, model height and size worn). Add Schema.org/SizeSpecification markup in the JSON-LD block. This is indexable by search crawlers and readable by most AI systems. It is static data that does not adapt to individual shoppers.

Option B — Shopify metafields you own (structured, per variant)

Hold fit attributes per product variant (fit type, size notes, model details) in metafields you define under Settings > Custom data > Products, so your theme and apps can show and reuse them. Whether an external agent can read them depends on how it integrates with Shopify, so check rather than assume.

Option C — Direct endpoint or API for agents (only if confirmed for your store)

If you want an agent to fetch fit information directly, discuss the specific store and workflow with the vendor. Integrations for APIs, agents or platforms are discussed per store; Rendered Fits does not present a public API contract. Confirm availability, authentication, scope and data handling first, and do not describe an endpoint publicly until you have tested it.

For most Shopify fashion brands today, the realistic starting point is Option A, with Option B where your theme uses it. Rendered Fits, a Shopify app, recommends a size from your size chart and fit notes and offers optional AI try-on previews to human shoppers, so complete size data helps both people and agents.

6. JSON-LD for fit — Schema.org and AEO extensions

Where fit data exists, it should be expressed in JSON-LD as well as in visible text. This makes it readable by any crawling agent or answer engine that parses structured data, without requiring an active API call.

The relevant Schema.org types are:

SizeSpecification — for declared size dimensions and size system (e.g. UKSize).
SizeGuide — for linking to or embedding a structured size guide.
ItemList combined with review data — for surfacing fit-consensus signals (for example, the share of reviewers who found a product true to size).

You can add this markup in your theme yourself. Whether a vendor can supply fit JSON-LD for your store is a per-store question, so confirm it before you plan around it.

7. Agent capability manifest — only describe what you have confirmed

An agent capability manifest is a machine-readable declaration of the endpoints and capabilities available at your store. Think of it as a sitemap.xml for agent interaction rather than content indexing. It tells AI shopping agents what data is available, how to access it, and what attribution to apply when those capabilities drive a sale.

A minimal fashion-store agent manifest might declare:

Which fit or sizing endpoints exist, if any, and what product IDs they accept.
Which structured fit data is available and in what format.
The attribution format expected when that data is used in a purchase recommendation.

Agent manifests are not a universal protocol: there is no single standard as of mid-2026, and agents do not universally check for one. OpenAI's Shopify integration and Google's Shopping Graph are both moving toward structured capability discovery, but a manifest is only useful if it is accurate. Publish one only for integrations you have confirmed and tested.

Before you publish a manifest or describe an integration

Availability: does the endpoint exist for your store today, and who runs it?
Authentication and scope: what can a caller read, and with what credentials?
Data handling: what shopper or product data is returned, stored or logged?
A test call: make one yourself and check the response matches what you plan to say.
Integrations are discussed per store. See Rendered Fits product facts; it is not a public API contract.

The full checklist at a glance

Area	What to do	Effort
1. Structured product copy	Material, fit type, length, care, origin in plain HTML text. Size table as crawlable HTML.	Low
2. Product JSON-LD	Schema.org Product with name, brand, image array, sku, offers, material, color, size, aggregateRating, review, sizeSpecification.	Medium
3. Page metadata	Keyword-led title. Attribute-rich meta description. Clean og:image.	Low
4. Reviews (on-site + off-site)	Schema.org Review + AggregateRating in JSON-LD. Natural-language reviews on-page. Off-site review syndication.	Medium
5. Fit / sizing information	Size guide and fit notes as on-page text. Fit attributes per variant in your own Shopify metafields. Any direct API or endpoint confirmed per store.	Low to medium
6. Fit JSON-LD	SizeSpecification in Product JSON-LD, added in your theme.	Medium
7. Agent manifest	Optional. Publish only for integrations you have confirmed and tested; there is no single standard yet.	Only if needed

Frequently asked questions

What is agentic commerce and why does it matter for fashion PDPs?

Agentic commerce refers to AI shopping agents — systems that research, evaluate, and complete purchases on behalf of consumers. McKinsey estimates these agents could mediate $3–5 trillion of global consumer commerce by 2030 and already account for 11–18% of B2C retail activity (BoF × McKinsey, State of Fashion 2026, p.42). For fashion brands, this means a growing share of purchase decisions will be made by systems that cannot see photographs, cannot interpret vague copy, and cannot guess at fit — they need structured, machine-readable data.

What structured data does a fashion PDP need for AI shopping agents?

At minimum: a Schema.org Product block with name, brand, description, image array, sku, and offers. Fashion-specific additions include material, color, size, aggregateRating, and sizeSpecification. For fit and sizing — the most important purchase-confidence factor in fashion — SizeSpecification markup and fit notes as plain text. Reviews should include natural purchase-language ("runs small", "true to size") marked up with Schema.org Review and AggregateRating.

How do I expose fit and sizing data in a machine-readable way on Shopify?

Start with what you control: (a) structured HTML text with SizeSpecification JSON-LD and a fit note per product; (b) fit attributes per variant in Shopify metafields you own; (c) if you want a direct endpoint or API for agents, discuss the specific store and workflow with the vendor. Integrations for APIs, agents or platforms are discussed per store, so confirm availability, authentication, scope and data handling before assuming one exists.

What is an agent capability manifest and do I need one?

An agent manifest is a machine-readable declaration of what capabilities are available at your store, analogous to sitemap.xml but for agent interaction. It is not a universal protocol requirement and there is no single standard yet. Only publish one that describes integrations you have confirmed and tested with the vendor.

What does McKinsey say brands need to do to be visible to AI shopping agents?

The McKinsey and Business of Fashion State of Fashion 2026 report (p.37, p.43) specifies two priorities: (1) "optimise for AI discoverability by overhauling product content and digital infrastructure so AI agents can readily access and read it"; (2) "semantically rich data and API-accessible content will be critical to success". The report also notes that brands absent from AI consideration sets "may as well be invisible" (p.44).

How is GEO different from traditional SEO for fashion brands?

Traditional SEO optimises for search engine crawlers indexing text and links. GEO — which McKinsey identifies as "the new SEO" (State of Fashion 2026, p.7, p.39) — optimises for AI answer engines and shopping agents that need to understand, evaluate, and cite products. The key shift for fashion is from keyword-dense text toward structured machine-readable data: JSON-LD schema, size charts and fit notes as text, and, where confirmed, agent integrations. Shopping-related searches on generative AI platforms grew 4,700% in a single year (2024–2025), making GEO a current commercial priority.

Can Rendered Fits add fit and sizing API endpoints to my Shopify store?

Integrations for APIs, agents or platforms are discussed per store. Rendered Fits is a Shopify app that recommends a size from your size chart and fit notes, builds outfits with Complete the Look and offers optional AI try-on previews. It is not a public API contract, and earlier blanket claims about universal production endpoints have been removed. Contact Rendered Fits to discuss a specific store, and confirm availability, authentication, scope and data handling first.

Sources

BoF × McKinsey — The State of Fashion 2026: When the Rules Change. Key figures cited in this page: 4,700% growth in AI-platform shopping searches (p.38); 53% of US gen-AI users used it to shop Q2 2025 (p.37–38); $3–5 trillion agentic commerce value by 2030 (p.42); 11–18% of B2C retail by 2030 (p.42); ~80% of AI-cited sources are third-party content (p.41); ChatGPT = 16% of Zara's inbound traffic (p.38, citing SimilarWeb); OpenAI/Shopify and OpenAI/Etsy deals (p.40, p.44); exec priority "optimise for AI discoverability" (p.37, p.43); "semantically rich data and API-accessible content" (p.37); GEO = "the new SEO" (p.7, p.39); "may as well be invisible" quote (p.44). mckinsey.com / businessoffashion.com
Schema.org — Product, SizeSpecification, SizeGuide, Review, AggregateRating. Markup references throughout. schema.org/Product
Google — Rich Results Test. For auditing PDP JSON-LD. search.google.com
Rendered Fits — product facts and integration enquiries. Integrations are discussed per store; the page is not a public API contract. renderedfits.com/for-ai-agents

How to make your fashion PDP readable by AI shopping agents — the agentic commerce checklist (2026)