Agentic Commerce: How AI Agents Buy Products via Shopify

Agentic commerce is changing how products get sold

AI agents are buying products. Not in two years. Now. According to Shopify's own figures, AI traffic to Shopify stores grew more than eight times year over year and orders from AI searches rose almost thirteen times, measured across the first quarter of 2026 against January 2025. The direction is clear: agentic commerce is growing into a serious purchasing channel, no longer an experiment.

This is not an abstract story. The Dutch online market is worth 35.7 billion euros. A growing share of those transactions does not start on your homepage, not through Google Ads and not through an Instagram ad. They start in a chat window. A consumer types "find me a good leather laptop bag under 80 euros" and an AI agent searches online stores, compares options and handles the purchase.

This is called agentic commerce. And over the past year Shopify has built a complete ecosystem for it.

This article explains how that ecosystem works, which protocols sit underneath it, how far the competition has come, and what it concretely means if you run an online store.

How do AI agents buy products?

An AI agent is not a chatbot. Where a chatbot answers questions, an agent carries out tasks. The difference is fundamental.

When a consumer asks ChatGPT to "find a red running shoe for wide feet, size 44, under 120 euros", the agent goes through several steps:

1. Discovery. The agent searches the product catalogues of online stores. With Shopify this happens through the Catalog API, which makes billions of products from Shopify merchants searchable for AI systems.

2. Evaluation. The agent compares products on specifications, price, availability, reviews and return policy. Not visually, but on the basis of structured data. JSON-LD schema, API responses, machine-readable product information.

3. Selection. Based on the user's criteria, the agent filters down to a shortlist. The agent can weigh in contextual factors: previous purchases, budget, location, delivery preferences.

4. Transaction. The agent starts a checkout. With Shopify this can run through the Checkout Kit, a JavaScript library that embeds checkout flows on any web page, or through Shop Pay, which is coming soon to Microsoft Copilot.

Every step in this process depends on data. No images, no atmosphere, no brand story in the classic sense. Pure structured, machine-readable information.

That is the heart of agentic commerce: your online store now has two audiences. People who scroll and look. And machines that read data and decide.

Which AI platforms already sell products via Shopify?

The channels are live. This is not a roadmap. This is what is running now.

ChatGPT Shopping. Hundreds of millions of users have access to the shopping feature. The agent searches for products, shows images, compares prices and links directly to the checkout of Shopify merchants. OpenAI rolled this out in 2025 and the use of AI shopping is growing fast.

Microsoft Copilot. Integrated into Windows, Edge and the Microsoft 365 suite. Thousands of Shopify merchants are already discoverable through Copilot. Shop Pay is coming soon as a payment method, allowing the full transaction to take place within the Copilot window.

Google Gemini. Google's AI assistant integrates product results into conversations via Shopify's Catalog API. The combination with Google Shopping data makes this one of the broader channels for product discovery.

Perplexity Shopping. Perplexity combines search with direct product recommendations. The agent compares options and shows purchase options with prices and availability. It is growing specifically among consumers doing comparative research before buying.

The pattern is clear. Every major AI player is building a shopping layer. And Shopify is the first partner at each of these platforms.

The protocols under agentic commerce: MCP, UCP, A2A and NLWeb

Agentic commerce does not run on one-off integrations. A protocol layer is emerging that defines how AI agents communicate with online stores. Four protocols form the foundation.

Model Context Protocol (MCP)

MCP was developed by Anthropic and is now supported by OpenAI, Google and Microsoft. It is the protocol that AI models use to access tools and data sources. The MCP SDK is downloaded tens of millions of times per month and there are now thousands of MCP servers running.

Shopify has built its own MCP server: the Dev MCP Server (@shopify/dev-mcp). It makes the Shopify developer platform "AI-native". Developers can use natural language to set up Shopify apps, run GraphQL queries and generate validated code for Liquid templates, UI extensions and Hydrogen storefronts.

For Shopify development this means, concretely: less searching through documentation, faster theming, fewer errors. The server runs locally and requires no authentication.

Universal Commerce Protocol (UCP)

UCP is the standard specific to agentic commerce. Co-developed by Google and Shopify, with backing from heavyweights: Walmart, Target, Etsy on the retail side. Visa, Mastercard, American Express and Stripe on the payment side.

UCP defines how an AI agent requests product data, starts a checkout and handles a payment. It is the common language between agents and online stores. Meta is already testing checkout experiences based on UCP.

A UCP manifest is a JSON file that you place at /.well-known/ucp. It tells agents which APIs are available, how the checkout works and what the return policy is. Shopify merchants can set this up through the new Agentic Plan, even without a full Shopify store.

Agent2Agent Protocol (A2A)

A2A was developed by Google with more than 150 organisations, including Salesforce, SAP and PayPal. The protocol governs communication between agents themselves. Think of a scenario where your personal shopping agent negotiates with an online store's customer-service agent about a return.

A2A is on version 0.3 and has been handed to the Linux Foundation.

Natural Language Web (NLWeb)

NLWeb comes from Microsoft and was conceived by R.V. Guha, the creator of RSS and Schema.org. It makes websites queryable in natural language. Every NLWeb instance automatically functions as an MCP server.

The practical implication: websites with existing Schema.org markup can make their content available to AI agents without extra development. Shopify, Tripadvisor and Eventbrite are early adopters.

These four protocols together form the infrastructure of the agentic web. It is not about a single integration with ChatGPT. It is a whole layer being built on top of the existing web.

Why Shopify beats WooCommerce, Magento and BigCommerce

Shopify's lead on agentic commerce is not subtle. It is a generational gap.

WooCommerce has an MCP integration in beta, launched in April 2026. It is opt-in: you have to activate, configure and maintain it yourself. WordPress 7.0 is building AI infrastructure, but focused on site management, not commerce. There are no native connections with ChatGPT, Copilot or Gemini. The WordPress developer community is, in its own words, "respectfully terrified" about the direction. WooCommerce is 12 to 18 months behind.

Magento (Adobe Commerce) has no native agentic commerce support. There is a community project for a Magento MCP bridge, but it is not officially supported. Adobe's own strategy focuses on content personalisation, not on agentic commerce. Any form of agent readiness on Magento requires custom development.

BigCommerce follows the open protocols. A UCP guide is available. But there are no MCP servers of its own, no AI Toolkit, no direct integrations with AI platforms. BigCommerce is a neutral player that moves along but does not lead.

If you are making the platform choice for a new online store right now, or considering a migration, this is the table that matters. Shopify is not by definition the best platform for every situation. But for agentic commerce readiness it is currently the only platform with a complete stack.

At Oase Creative we build Shopify stores and now include agentic readiness as standard in every new build. Not as an upsell. As part of an online store that is ready for how e-commerce works in 2026.

What does agentic commerce mean for the Dutch market?

The Dutch e-commerce market has specific characteristics that nuance the agentic commerce story.

Checkout is not live in Europe yet

ChatGPT Instant Checkout, the feature that lets a user pay directly without leaving the chat, is live for Etsy in the US. Shopify is following soon. But Europe is not up yet.

The reasons are concrete:

• Payment preferences. Dutch consumers pay with iDEAL, not credit cards. Belgian consumers use Bancontact. Klarna is big in Scandinavia. Shop Pay has to support these methods before European checkout works.
• Regulation. PSD2 (Strong Customer Authentication) requires extra verification steps for online payments. GDPR sets limits on how product data and customer data are shared with AI platforms.
• Phased rollout. Shopify rolls out checkout features country by country. The US first, Europe later.

Product discovery already works

The checkout may not be live in the Netherlands yet, but product discovery through AI already works fully. When a Dutch consumer asks ChatGPT or Copilot for product recommendations, Shopify merchants are included in the results. The agent links to the checkout on your store.

This is where the opportunity sits right now. Not in the transaction layer (that is coming), but in the discovery layer (that is running).

No Dutch agency is writing about it

Emerce published a background article on agentic commerce and product data in February 2026. Twinkle wrote a two-part series on the AI consumer in January. A single Shopify agency wrote about ChatGPT Instant Checkout.

But nobody in the Dutch market is writing about the Shopify AI Toolkit, the protocols under agentic commerce, or the practical implementation for Dutch online stores. There is a content gap and an expertise gap. Many e-commerce companies are still working on standardisation for agentic AI, and a substantial share have not even started.

Dutch online stores that invest in agentic readiness now are building the same kind of lead as the early SEO investors ten years ago. With one difference: the adoption curve is steeper. SEO had years to mature. Agentic commerce compresses that into months.

The Shopify AI Toolkit: what it does and why it matters

On 9 April 2026, Shopify launched the AI Toolkit. This is a plugin that integrates Shopify's developer platform into five AI code editors: Claude Code, Cursor, VS Code, Gemini CLI and OpenAI Codex.

What it does:

• Full Shopify documentation searchable from inside your code editor
• API schema references for GraphQL and REST endpoints, validated live
• Code validation against Shopify's own schemas (Liquid templates, GraphQL queries, UI extensions)
• Store management through CLI integration, directly from your editor
• Automatic updates that sync with platform changes

The toolkit is open source (MIT license), built in Node.js, and configured through MCP server settings.

For developers this is a productivity jump. No tabs of documentation open. No searching for the right API call. The editor knows what Shopify can do and validates your code on the spot.

But the toolkit is more than a developer tool. It is a signal. Shopify is not only investing in agentic commerce for consumers. It is investing in agentic development. The entire chain, from building to selling, is becoming AI-native.

For SEO this matters too. The Catalog API that sits under the toolkit makes product data searchable for AI systems. Schema.org markup on your store is no longer just a way to be found in AI search engines. It is also your agentic commerce foundation. Structured data is your AI storefront.

How do you prepare your store for agentic commerce?

The protocols are in place. The channels are live. What do you need to do concretely now?

Product data as a strategic asset

This is the most important shift. Product data is no longer a technical detail you leave to your ERP system. It is a strategic asset.

AI agents do not read marketing language. "Premium quality" is worthless to an agent. "Full-grain leather, 2 mm thick, water-repellent, 350 grams" is usable. The first 60 to 100 words of your product description have to be factual. Product type, materials, dimensions, specifications. The brand story comes only after that.

Every product variant (size, colour, finish) needs its own structured data with current availability. An agent that recommends size 44 while it is sold out quickly learns to avoid your store.

Structured data as the foundation

JSON-LD Product schema on every product page. Not optional. Product, AggregateRating, MerchantReturnPolicy, every field filled in: name, description, price, availability, brand, SKU, GTIN/EAN.

In addition: a UCP manifest at /.well-known/ucp that tells AI agents how they can interact with your store. Which APIs are available, what the payment methods are, how the checkout works.

Speed as a ranking factor

AI agents compare several online stores at once. They work in decision windows of 500 milliseconds. If your Storefront API responds more slowly than your competitor's, you lose the recommendation. Just as load time is a ranking factor for Google, API response time is a ranking factor for AI agents.

The 90-day roadmap

• Day 1 to 30: Product data audit. Implement JSON-LD schema on all product pages. Set up real-time data synchronisation between your inventory and your storefront.
• Day 31 to 60: Document the Storefront API. Optimise cart and checkout APIs. Set up authentication and rate limiting for agentic traffic.
• Day 61 to 90: Dynamic pricing API. Shipping calculator. Full test of the flow from discovery to checkout.

This is not a theoretical roadmap. It is based on what Shopify merchants are doing right now to become discoverable for AI agents.

The future of agentic commerce: what is still coming?

Agentic commerce is at the beginning. What is live now is version 1.0. This is what is coming.

Autonomous purchases. Right now the consumer still confirms every purchase. Within two to three years consumers will delegate repeat purchases entirely to agents. "Order my coffee every month, find the best price." The agent buys without intervention.

Agent-to-agent negotiation. Through the A2A protocol, consumers' agents will negotiate with online stores' agents. About price, delivery time, bundles. The consumer only sees the end result.

Brand identity for machines. Branding becomes twofold. Your visual identity for people. And your data identity for machines. Consistent, reliable, fast data becomes the equivalent of a strong brand. Agents learn which stores supply reliable information and give them preference.

Consolidation onto Shopify. Brands that do not use an e-commerce platform now but do want to be discoverable for AI agents can add their products to the Catalog through Shopify's Agentic Plan. Without a store. Just data. This lowers the barrier to participate and grows Shopify's network.

The brands that start with agentic readiness now are building transaction history and trust signals with AI agents. That is a compounding effect that latecomers cannot close by spending more money later. Just like SEO, only faster.

Frequently asked questions about agentic commerce and Shopify

What exactly is agentic commerce?

Agentic commerce is the phenomenon where AI agents search for, compare and buy products on behalf of consumers. The consumer gives an instruction in natural language ("find a good espresso machine under 500 euros") and the agent searches online stores, compares options and in some cases can check out directly. Shopify is the first platform with full native support for this.

Which AI platforms can customers already buy products through?

ChatGPT Shopping, Microsoft Copilot, Google Gemini and Perplexity Shopping are the main channels. Hundreds of millions of ChatGPT users have access to the shopping feature. Thousands of Shopify merchants already sell through Copilot. Google integrates product results into Gemini via the Catalog API.

What is the Universal Commerce Protocol (UCP)?

UCP is an open standard for agentic commerce, co-developed by Google and Shopify. It defines how AI agents request product data, start checkout and handle payments. UCP is supported by Walmart, Target, Etsy, Visa, Mastercard, American Express and Stripe.

Does agentic commerce only work on Shopify?

No, but Shopify is by far the furthest ahead. WooCommerce has an MCP integration in beta that has to be activated manually. Magento has no native support. BigCommerce follows the protocols but lacks tooling of its own. Shopify is the only platform with the complete stack: native MCP server, Catalog API, Checkout Kit and direct integrations with all the major AI platforms.

Is agentic commerce relevant for the Dutch market?

Yes. The checkout integration is not live in Europe yet because of iDEAL, PSD2 and GDPR. But product discovery through AI already works fully. Dutch online stores that get their data in order now are building a lead that can no longer be closed later. Many e-commerce companies are still working on standardisation, a substantial share have not started.

How quickly do I need to act on this?

Now. Growth is fast: more than eight times as much AI traffic and almost thirteen times as many AI orders year over year, according to Shopify's own figures. Early movers build trust signals with AI agents that latecomers cannot catch up on. Start with a product data audit and a structured-data implementation.