OpenAI Product Feeds: From Catalogs to Conversations

Search has always loved structured data. For years we’ve shipped well-formed product catalogs to Google Merchant and tuned attributes to win in Shopping. That mental model still helps—but OpenAI’s new commerce feed is drastically evolving the game. We’re no longer optimizing static listings for a SERP; we’re supplying machine-readable context to an assistant that negotiates intent in real time.

Here’s how it’s different and how we’ll approach it with semantic data.

What’s fundamentally different

I spent a few hours tinkering and reviewing the specifications and reading a few of the early commentary. Here is my take:

1) From “listing” to “reasoning input.”
A Google Merchant feed describes a product so it can be ranked and priced in a comparison grid. An OpenAI feed becomes evidence the assistant uses while reasoning inside a conversation. Attributes aren’t merely filters; they’re facts the agent mentions, contrasts, and turns into answers.

2) From keywords to use-cases.
Google expects taxonomy + attributes. OpenAI benefits from use-case semantics: what the product is for, what it pairs with, who it fits, and under what constraints (budget, materials, delivery window, accessibility, sustainability). Think “compatible with iPhone 15 Pro,” “works for cold brew,” “fits 28–30″ waists,” “vegan leather,” “next-day in Milan.”

3) From click-through to task completion.
Shopping ads chase CTR and conversions off-site. Agentic commerce optimizes for problem resolution in-chat: shortlisting, trade-off explanations, bundle suggestions, and—if enabled—instant checkout. The quality bar shifts from glossy creatives to clean facts, variant logic, inventory freshness, and clear policies. Remember, ChatGPT controls its own memory of you.

4) From one PDP to many variants.
Assistants excel when they can reason across variants (size, color, region, price, fulfillment). That means embracing item_group_id + per-SKU offers, not flattening everything into the parent. Variant hygiene is no longer optional. GS1 Digital Link data is foundational for higher-quality, context-aware product interactions, delivering a distinctive experience across categories. And the magic doesn’t stop online, these experiences can flow naturally into local retail.

5) From periodic uploads to near-real-time truth.
Google tolerates slower cadences. Assistants need fresh stock, price, and delivery estimates to avoid hallucinations and broken promises. Treat availability and shipping as live signals, not static attributes.

What the OpenAI feed wants (practically)

• Identifiers that won’t wobble: stable id (SKU/offer), item_group_id for variants, plus GTIN/MPN when you have them.
• Plain-text clarity: descriptions without HTML; avoid marketing fluff that can’t be reasoned over.
• Rich, typed attributes: condition, materials, dimensions with units, compatibility, care instructions, warranty.
• Related products: accessories, add-ons, and upgrades that enhance compatibility, expand capabilities, or improve performance.
• Media that proves it: primary + additional images; video or 3D where useful.
• Commercial truth: price with currency, sale windows, inventory quantity, preorder/ETA.
• Fulfillment reality: shipping regions, costs, and delivery estimates (ideally per region/warehouse).
• Policy surfaces: returns, privacy, terms, seller identity. These build trust and unlock checkout.

If you also enable Instant Checkout, plan for the server-side bits (checkout session endpoints, order notifications, payment token handling). It’s closer to an integration than a feed.

A KG-first blueprint for product feeds

1) Model products are entities, not rows.
Our Knowledge Graph already expresses Product Offer Organization Place. We’ll map entities to feed records while preserving relationships the assistant can use (brand lineage, compatibility, accessories, store locations).

2) Promote use-case facts to first-class fields.
We’ll extract and normalize attributes that answer “Will this work for me, here, now?”—sizes (with systems), fit, allergens, power standards, region availability, and compatible devices. These become reason-ready snippets the agent can quote.

3) Treat variants as citizens.
Each variant gets its own entity with a shared item_group_id. Parent PDP stays canonical; variants carry offer-level price, stock, personalized description and media.

4) Keep the truth fresh.
We already join, in most cases, the KG with inventory/OMS and pricing to keep availability, inventory_quantity, and shipping promises current. Stale data erodes trust; assistants remember. This will become even more interesting when the local inventory as well are added to the mix.

5) Make policies explicit and linkable.
Clear, crawlable URLs for returns, privacy, and terms—plus seller name and contact—are mandatory for assistant-mediated trust and checkout eligibility.

6) Write like we’re talking to a colleague.
The assistant isn’t swayed by superlatives. We write descriptions, product highlights and details that are specific, comparable, and testable: materials, tolerances, standards, care, and limitations. All of this is done already at scale using our Content Generation tool.

The mindset shift

Google Merchant rewards catalogs that rank. OpenAI rewards knowledge that helps—facts an assistant can rely on to guide someone to the right choice, confidently and quickly. That’s where structured data and graph thinking change the game.

With a Knowledge Graph as the source of truth, we don’t just list products—we model the domain and the language around it:

• Domain entity graph: products, offers, brands, categories, compatibility (“works with”), substitutes, bundles, store locations, return policies—typed and linked with Schema.org/GS1. This gives the agent grounded relationships to reason over (e.g., “this filter fits the Aeropress; this lens is for Nikon Z-mount; this size maps to EU 42”).
• Lexical graph: the text side—chunked PDP copy, specs, care instructions, size guides, manuals, reviews, and structured Q&A. We attach each chunk to the right entities, so the assistant can quote precise, verified passages instead of guessing.

The combination is powerful: the entity graph tells the agent what is connected to what; the lexical graph supplies the exact words and evidence to answer follow-ups (“how to clean it,” “is it vegan,” “will it arrive by Friday in Milan?”). This is the difference between a shoppable catalog and an assistant-ready product memory.

Practically, we ship three things in the feed (and keep them fresh):

1. Facts: identifiers, price, stock, variants, dimensions with units, compatibility.
2. Context: use-case attributes (fit, allergens, power standards, regional availability) and policy surfaces (returns, warranty).
3. Evidence: linked text chunks and Q&A snippets the agent can cite verbatim.

OpenAI (and any other AI Agent) then has everything it needs to explain trade-offs, propose bundles, and complete tasks—not just rank SKUs. With a semantic layer (a Product Knowledge Graph), you’re ready to ship not just products, but understanding.

Make your catalog agent-ready with WordLift B+. Start your Product Knowledge Graph today.

Agentic Commerce Protocol (ACP): fundamentals, tech & adoption

What are the key technical components of the ACP architecture?

Think of ACP as a universal language that allows AI agents, merchants, and payment systems to communicate securely and efficiently. It’s an open standard designed for interoperability.

The core components include:

• Agent & Intent Schema: A standardized format for an AI agent to express a user’s goal, such as the intent to purchase a specific product with defined constraints (e.g., budget, delivery time).
• Capability Discovery: A mechanism for merchants to advertise their capabilities—what products are in their catalog, current pricing, availability, and shipping options—so agents can discover them.
• Standardized Checkout API: A consistent, predictable flow for an agent to build an order, get the user’s approval, and authorize payment.
• Authentication & Consent: A secure system of temporary tokens and consent records that allows an agent to act on a user’s behalf, with a clear audit trail that the user can revoke at any time.
• Pluggable Payment Layer: An adaptable interface that connects to various payment processors (like Stripe) and methods (such as credit cards or digital wallets).
• Post-Purchase Webhooks: Standardized event notifications for fulfillment processes, including inventory updates, shipping confirmations, and returns.
• Security & Auditing: A framework for cryptographically signing key messages and maintaining detailed logs to prevent fraud and resolve disputes.

Is the Agentic Commerce Protocol compatible with blockchain technologies?

Yes. While ACP is blockchain-agnostic—meaning it does not require a specific ledger technology—it is fully compatible with them. Businesses can integrate blockchain where it adds distinct value, such as:

• Auditing & Provenance: Using a permissioned ledger (like Hyperledger) to create an immutable audit trail for enterprise compliance.
• Digital Assets: Leveraging public chains (like Ethereum) for commerce involving tokenized assets or NFTs.

In essence, ACP can operate with traditional payment systems, blockchain-based ones, or a hybrid of the two.

What are some real-world applications of the Agentic Commerce Protocol in 2025?

As of late 2025, ACP is enabling a new wave of frictionless, AI-driven commerce. High-impact applications include:

• Conversational Checkout: Users can ask a generative AI assistant (like ChatGPT) for a product, and the agent can complete the entire purchase within the conversation, as seen in pilots with merchants on Etsy and Shopify.
• Automated Personal Shopping: AI agents that automatically reorder household essentials, dynamically selecting the best merchant based on real-time price, availability, and delivery speed.
• Complex Itinerary Booking: Travel agents that seamlessly assemble and purchase multi-part journeys, booking flights, hotels, and insurance across different providers in a single, unified process.
• B2B Procurement Automation: Business assistants that autonomously negotiate for standard products (SKUs) and trigger purchase orders when inventory levels are low.

How does ACP enable AI agents to create personalized shopping experiences?

ACP provides the standardized framework for communication and consent that AI agents need to act on a user’s unique preferences. It allows an agent to:

• Understand User Constraints: Pass critical information like budget, brand preferences, or dietary restrictions to a merchant system.
• Query Merchant Capabilities: Ask for specific product variants, sizes, or delivery windows.
• Execute Tailored Purchases: Leverage rich metadata from merchants—such as product bundles or custom fulfillment options—to create a hyper-personalized selection and checkout flow for the user.

This eliminates the need for custom, one-off integrations for each merchant, allowing any agent to provide a personalized experience with any ACP-enabled business.

What are the primary business benefits of implementing ACP?

For businesses, adopting ACP offers a significant competitive advantage by making their products and services “agent-native.” Key benefits include:

• Increased Revenue: Reduce friction and cart abandonment by enabling customers to make purchases directly within AI-powered conversations.
• Broader Discovery: Position your products to be recommended by AI agents, opening up a powerful new discovery and sales channel.
• Future-Proofing: Become an early adopter of the new standard for AI-driven commerce, ensuring your business is ready for the next wave of digital interaction.
• Reduced Integration Costs: A single implementation allows you to interoperate with a growing ecosystem of AI agents and platforms, minimizing the need for costly, bespoke engineering work.
• Standardized Security: Leverage established payment partners (like Stripe) for secure, reliable payment processing and liability handling.

What are the key challenges or considerations when adopting ACP?

Adopting any new protocol requires strategic planning. Key considerations include:

• Systems Integration: Mapping legacy catalog, inventory, and fulfillment systems to the standardized ACP data schema.
• Operational Readiness: Preparing to handle new types of requests from agents, such as complex fulfillment logic or multi-part shipments.
• Customer Experience: Designing a seamless user experience where customers feel in control and understand how agent recommendations are generated.
• Compliance & Regulation: Navigating the evolving legal landscape for AI, payments, and consumer data protection.
• Fraud Prevention: Implementing clear protocols for handling disputes and preventing fraud in agent-mediated transactions.

What is the market adoption rate of ACP in late 2025?

As of late 2025, ACP is in its initial commercial rollout phase. The protocol was introduced by OpenAI and Stripe with the launch of “Instant Checkout” in ChatGPT, featuring Etsy as the first live merchant partner and Shopify integration announced to follow.

While a global adoption percentage has not yet been published, the open-sourcing of the protocol is expected to accelerate adoption significantly across the e-commerce and payments ecosystem.

How does ACP differ from a traditional e-commerce platform?

The key difference is that ACP is a protocol, not a platform.

• A traditional e-commerce platform (like Shopify or Magento) is a hosted storefront designed for human interaction via a graphical user interface (GUI).
• ACP is an interoperability protocol that defines a standard for programmatic commerce, allowing autonomous AI agents to discover products and transact on a user’s behalf.

It is designed for machine-to-machine communication, with an emphasis on consent tokens, agent intent, and machine-readable catalogs, rather than human-driven clicks.

How can ACP be used to optimize supply chain management?

ACP provides standardized, real-time signals about product availability, lead times, and fulfillment options. This allows intelligent agents to automate and optimize supply chain operations by:

• Automating Reorders: Triggering purchase orders automatically when inventory hits a predetermined threshold.
• Dynamic Sourcing: Querying multiple suppliers to find the best option based on current stock levels and delivery times.
• Just-in-Time Ordering: Enabling agent-driven intelligence to reduce stockouts and minimize carrying costs.

When integrated with existing enterprise resource planning (ERP) systems, ACP can significantly improve supply chain efficiency and resilience.

What are the potential legal and regulatory implications of agentic commerce?

As of 2025, regulators globally are actively developing frameworks for AI and commerce. Key areas for businesses to monitor include:

• Consumer Protection: Defining liability and return policies for purchases made by an agent on a user’s behalf.
• Payment Regulation: Ensuring compliance with KYC (Know Your Customer) and AML (Anti-Money Laundering) rules for programmatic transactions.
• Data Privacy: Adhering to regulations like GDPR and CCPA regarding consent records, data portability, and the right to deletion.
• Advertising & Disclosure: Maintaining transparency in how AI agents make recommendations to avoid potential conflicts of interest.

Implementers should prioritize building explicit user consent flows and maintaining robust, auditable records.

How does the Agentic Commerce Protocol handle user data privacy?

The ACP framework is built on core principles of data privacy and user control:

• Explicit Consent: Agents can only act on a user’s behalf with an explicit, revocable consent token.
• Scoped Permissions: Agent actions are limited to authorized scopes, preventing overreach.
• Data Minimization: The protocol encourages agents to request only the data fields necessary to complete a transaction.
• Auditability: Users can review a clear log of their agent’s actions, ensuring transparency.

While the exact implementation depends on the vendors involved, the protocol’s design prioritizes user privacy.

What industries are most likely to benefit from ACP adoption?

ACP is poised to add significant value to industries characterized by complex purchases, repeat orders, or the need for dynamic discovery.

Early adopters are likely to be in:

• Retail & E-commerce: Particularly marketplaces and direct-to-consumer (DTC) brands.
• Travel & Hospitality: For assembling complex, multi-part bookings.
• B2B Procurement: For automating repeat orders and sourcing standard SKUs.
• Subscription Services: For managing automated reorders of groceries, medications, and other consumables.
• Digital Goods: Including marketplaces for NFTs or other tokenized assets where agent-driven discovery can accelerate transactions.

What are the most recent major announcements regarding ACP in 2025?

In late September 2025, OpenAI, in partnership with Stripe, officially launched the Agentic Commerce Protocol (ACP). This launch coincided with the release of “Instant Checkout” inside ChatGPT, a feature that allows users to complete purchases conversationally.

Instant checkout, ChatGPT + Stripe, security, comparison

What is Instant Checkout, and how does it work in ChatGPT?

The post OpenAI Product Feeds: From Catalogs to Conversations appeared first on WordLift Blog.