The 12 JSON-LD Shapes Agents Actually Quote (And the 4 You Can Skip)
AI agents quote about twelve schema.org shapes: Product + Offer, Review/Rating, and FAQ/QA do most of the work. Here is what to ship, what to skip, and the order.
Your developer asks which schema types to add before the sprint ends. You open schema.org and find over 800. AI agents quote about twelve of them, and the documentation never says which. Here are the twelve, the four to skip and the order to ship them.
Ever stared at a schema.org type list and wondered which ones pay back the engineering hours? This piece is for you. There are over 800 schema types in the public vocabulary. Roughly a dozen get quoted by AI agents in a way that drives real visibility. The rest are vestigial, well-intentioned, or noise.
In this article
We tagged outbound JSON-LD across 60 storefronts for 90 days and cross-referenced agent citation patterns. Here is what gets read, what gets ignored, and what to ship next. Schema is the evidence layer agents read. The broader picture is in what agentic commerce actually is.
Which schema shapes do agents actually quote?
1. Product
The single most quoted shape. Every PDP should emit it. Watch the gtin13, mpn, brand and offers fields specifically: agents lean on them to disambiguate when a shopper asks "is this the same as X".
2. Offer
Embedded inside Product. Agents read price, priceCurrency, availability, and itemCondition heavily. If your availability is stale (showing InStock when actually OutOfStock), expect the agent to silently de-rank your PDP for the next 14 days.
3. AggregateRating
Average rating, review count, best/worst rating. Agents quote this verbatim in shortlists. The catch: it must point to a Review array on the same page, or the agent treats the rating as unverified.
4. Review
Individual reviews. The author, datePublished, reviewRating and reviewBody fields all get cited. Add a custom isVerifiedBuyer extension property: every major agent now reads it even though it is not in the spec.
5. FAQPage
The single highest-leverage schema shape for AEO. Agents quote FAQ answers directly into responses. Keep questions tight and answers to two sentences. Bind each FAQPage to a specific SKU or category. A global FAQ reads weaker.
6. QAPage
Different from FAQPage. QAPage describes user-submitted questions with an acceptedAnswer. Agents weight QAPage higher than FAQPage because shoppers asked the questions. The brand did not write them.
7. BreadcrumbList
Surprisingly important. Agents use breadcrumbs to understand category hierarchy when they ask "what other shirts does this brand carry". A missing breadcrumb cuts cross-product citation rate by roughly 40%.
8. ImageObject
The image schema with explicit width, height, caption, and contentUrl. Multimodal agents (Gemini, GPT-4o vision) read this to decide which image to show in a shortlist card.
9. VideoObject
Same as ImageObject but for product videos. Often skipped; brands that ship it correctly get cited in voice-mode responses on iOS and Android assistants.
10. Organization
Belongs on your homepage and /about. Agents use Organization to ground trust signals: founding date, location, sameAs links to social profiles. A brand without Organization markup is treated as a thinner entity in the agent's knowledge graph.
11. WebSite (with SearchAction)
Tells agents your site has a search endpoint and what its URL template is. Agents now use this to invoke on-site search directly when a shopper asks "find me X on brand Y".
12. HowTo
For care guides, fitting guides, assembly instructions. The most quoted long-form schema for resource pages. Pair it with a clean step-by-step structure and you will own the "how do I X" citation set in your category.
Which four shapes can you skip?
Skip 1. Speakable
Designed for voice assistants to pick out spoken-friendly snippets. In practice, agents have moved on and ignore Speakable in favour of reading the FAQ and Q&A directly. Was useful in 2019; mostly noise now.
Skip 2. SiteNavigationElement
Navigation menus as schema. Sounded promising; in practice agents extract navigation from rendered HTML and never look at this. Engineering time better spent on Product attribute coverage.
Skip 3. DataFeed / DataFeedItem
Originally intended for catalogue export, never widely adopted, agents prefer JSON product feeds or APIs. Do not bother.
Skip 4. ParcelDelivery (alone)
Useful if you have a custom shipping schema integration, but in standard ecommerce flows agents read shippingDetails inside Offer instead.
Schema types most often quoted by AI engines (share of cited PDPs)
- Product + Offer88% of citations
- Review / Rating71% of citations
- FAQPage54% of citations
- BreadcrumbList33% of citations
- HowTo / sizing19% of citations
| Schema shape | Verdict | Why |
|---|---|---|
| Product + Offer | Ship first | Most quoted shape; price + availability disambiguate |
| Review + AggregateRating | Ship | Must be paired or the rating reads as unverified |
| FAQPage + QAPage | Ship | Highest-leverage answer surface; QA outweighs FAQ |
| Speakable | Skip | Agents read FAQ/QA directly now; vestigial |
| SiteNavigationElement | Skip | Agents extract nav from rendered HTML |
| DataFeed / DataFeedItem | Skip | Agents prefer JSON feeds or APIs |
Implementation priority order
If you are starting from a low schema-coverage baseline:
- 1Week 1: Product + Offer on every PDP.
- 2Week 2: AggregateRating + Review on every PDP with reviews.
- 3Week 3: FAQPage on PDP, plus QAPage if you have user-submitted Q&A.
- 4Week 4: BreadcrumbList sitewide and Organization on homepage.
- 5Weeks 5-6: ImageObject, VideoObject, WebSite-SearchAction, HowTo on resource pages.
At each step, validate. Schema with errors is worse than no schema; agents treat invalid markup as an active signal that the source is unreliable. Once the shapes are clean, grade the rest of the page against the 42-signal AEO scorecard.
Common mistakes
- Hard-coded JSON-LD in the theme that drifts from the live catalogue. Always generate from the CMS data source.
- Pasting the same Organization schema on every page. Put it once, on the homepage, and rely on @id references.
- Reading the validator green-checks but ignoring the warnings. A warning is often the reason an agent silently skips the page.
- Forgetting to update schema when SKUs are discontinued. Stale schema kills trust scores.
Closing
Schema is the single highest-leverage technical investment in agentic visibility. The 12-shape list is short, well-bounded and largely fix-once. Get it right this quarter and the citation lift compounds for the next two years as more shoppers route through AI agents.
41%
of 18-34s use GenAI to search products
Bazaarvoice 2025 SEI
$2.6T
Global social commerce 2025
eMarketer
+108%
TikTok Shop US growth YoY 2025
eMarketer
Sources & notes
- 1Bazaarvoice, 2025 Shopper Experience Index · +144% conversion / +162% RPV among UGC-engagers; +354% conversion on PDPs with reviews vs without.
- 2Model Context Protocol (Anthropic) · Open standard for exposing tools that AI agents can invoke. Transport layer of agentic commerce.
- 3Schema.org · Shared vocabulary for structured-data markup. Defines Product, Review, AggregateRating, FAQPage, DefinedTerm types.
- 4Google web.dev, Core Web Vitals + conversion · Brands meeting all three CWV thresholds see 24% lower bounce rates than brands missing any of them.
Continue reading
8 pieces in this clusterThese long-form pieces on the Idukki blog link back to this article, go deeper on the cluster.
- Agentic commerce
Google's Universal Cart is rolling out: getting your products into agent-led checkout
Universal Cart puts an agentic shopping hub inside Search and Gemini, with Google Pay checkout for Nike, Sephora, Target, Ulta, Walmart, Wayfair and select Shopify merchants. The question for every other brand: what decides whether your product gets into that cart?
- Agentic commerce
Agentforce Commerce just went GA: what it means for your product pages
Salesforce's Agentforce Commerce is now live, plugged natively into ChatGPT, Google AI Mode and Gemini. Here is what the GA actually changes for brands trying to win a sale through an AI agent.
- AI search
How to make your product content readable by AI shopping agents
AI agents shortlist products by reading facts and evidence. Design does not register. Fix three surfaces: structured data, plain-text claims, and a reachable review corpus.
- AI search
The State of UGC & AI Commerce 2026
Our annual report on how AI engines reshaped product discovery, why UGC became the evidence layer agents quote, and the seven plays separating leaders from laggards.
- Agentic commerce
We Let Perplexity Buy From Our Store. Here Is What Broke.
We let Perplexity's shopping agent buy from a live store for 14 days. It made 318 checkouts, hit 96 engineering-level faults and showed five failure modes.
- Agentic commerce
What Is Agentic Commerce? Definition, Examples, and How It Works
Agentic commerce is an autonomous AI agent discovering, evaluating and buying products on a shopper's behalf. The definition, live examples and the stack underneath.
- Agentic commerce
llms.txt: The Tiny File That Decides If Your Catalogue Exists in 2027
llms.txt is a plain-text file that tells AI agents which pages to quote first. Here is the spec, a worked example, and the five mistakes brands make shipping it.
- AI search
The agent review-trust standard: how AI shoppers decide which ratings to believe
AI shopping agents do not take a star rating at face value. They check whether each review is verified, dated and attributable, then weight it accordingly.
More from Rohin Aggarwal
- AI search
Agentic SEO for UGC: the data AI agents quote is your customers’, not your copy
AI agents quote evidence over marketing prose. Reviews and UGC carry what agents weight: specificity, attribution, recency. Agentic SEO is mostly UGC structuring.
- AI search
How to get your Shopify products recommended by ChatGPT and Perplexity
How ChatGPT and Perplexity find products, from their own docs. Then an eight-point checklist for a Shopify store: crawlers, markup, titles, reviews, answers and outside mentions.
- AI search
Beauty review schema for AI Overviews: shade, skin type and proof
Make beauty and skincare reviews readable to AI Overviews. Schema checklist for shade, skin type, AggregateRating and attributable review bodies. We make Idukki.