Skip to content

Blog · Published · Updated

UCP (Universal Commerce Protocol): what it is and when it applies to a store in the EU

Short answer

UCP, the Universal Commerce Protocol, is an open standard from Google and Shopify through which an AI agent finds a store's products, builds a basket and runs the purchase. According to Google, buying through UCP in AI Mode and Gemini today covers eligible products in the US, Canada and Australia, for selected merchants. A store in the EU prepares its product data and measurement now.

How we workDetails ↓

  1. 01Call30 minutes with an engineer, free
  2. 02PrototypeA working system on your process and data, free
  3. 03ImplementationTarget and fixed price in the contract; 50% at signing
  4. 04Acceptance50% once the agreed target is met
net for the automation of one process, paid once
from €3,000
from signing the contract to acceptance
2–6 weeks
free prototype on your cases
€0

We belong to the OpenAI and Anthropic partner programmes and learn through their official courses. What this means ↓

Author: Syntalith · 3 min read

Example: the morning request inbox
Agent · ready

Statistics

Purchases by AI agents: statistics 2026

3 countries

covered by UCP purchases in AI Mode and Gemini according to Google: the United States, Canada and Australia, for selected merchants. The EU is outside that scope.

Figures checked: 22 October 2026

How UCP works

The store publishes a profile in a JSON file at /.well-known/ucp. The profile describes the store's features, for example checkout, discounts and delivery, and the payment methods it supports. The agent fetches the profile, compares it with its own capabilities and uses the part they share (Google Developers Blog).

ElementWhat it means for the store
Featuresthe store chooses what to offer: checkout, discounts, delivery, orders
Extensionsits own features, for example a loyalty programme, in the namespace of the store's domain
Transporta REST API, MCP or A2A, depending on the store's technology
Paymentsthe store names the providers, and the agent picks one
Handover to a personthe buyer finishes the purchase in an embedded checkout

Shopify Engineering describes how, when a merchant requires something the agent cannot do, the agent fills in what it can and the buyer completes the rest in an embedded checkout.

How UCP differs from ACP and WebMCP

UCP is the Google and Shopify standard for purchases in AI Mode and Gemini. ACP is developed by OpenAI with Stripe, and since March 2026 it has mainly carried product feeds into ChatGPT. WebMCP in Shopify is a set of checkout tools for agents that run in the buyer's browser. All three use the same product data from the store, so work on variants, units and availability pays off in every channel. They differ in who runs the purchase and where the payment happens: with UCP in Google the payment goes through Google Pay, and with WebMCP it goes through the store's checkout with the buyer's confirmation.

What the merchant keeps

Merchant Center Help says the merchant remains the seller of record and can adapt the integration to its checkout requirements. The buyer pays through Google Pay with payment methods and an address from Google Wallet. The buy button appears only on products with the native_commerce attribute, and taking part requires an application to the early access programme. According to Google, UCP is compatible with A2A, AP2 and MCP.

A purchase through UCP in AI Mode or Gemini
  1. 01Profile/.well-known/ucp with features and payments
  2. 02Discoverythe agent finds the product in the store's data
  3. 03Basketvariant, quantity and delivery according to the profile
  4. 04PaymentGoogle Pay with details from Google Wallet
  5. 05Orderthe merchant as the party to the transaction

What a store in the EU can do now

Preparing before UCP reaches your country
  • A complete Merchant Center feed with variants and availability
  • Prices, delivery and returns in the page text, readable without images
  • Unambiguous variants and units of sale
  • Measurement of visits and sales from AI assistants
  • Agent requests labelled in your logs once they appear in your country

You can recognise requests from Google by the UCP-Agent header and a User-Agent that starts with „Google/UCP”, so it is worth labelling them in your logs and reports from the start. Shopify co-created UCP and offers it to merchants in its Agentic Storefronts channel (Shopify). A general description of purchases by agents is published by Shopify, and technical questions are answered in Google's UCP FAQ.

What to do, depending on the store
  • A store on Shopify

    Agentic Storefronts settings and the quality of product data

    configuration

  • A store on another platform, selling in the EU

    a Merchant Center feed, data on the page and measurement

    audit from €600

  • A store with its own system, selling to the US, Canada or Australia

    a UCP profile and a checkout integration

    from €3,000

A comparison of UCP with ACP, MCP, A2A and AP2 is in AI agent protocols compared, and the plan for a store in agentic commerce. Status checked on 22 October 2026. For the free analysis, bring your store's address and the countries you sell to.

Worked example · Scenario

How we count the payback: an online store

We run the same count for your store in the free analysis.

€2,792

a month for handling 800 orders that bypass the checkout

Payback: 1.3 mo.

6 minutes to retype an order or answer a question and checking in 15% of the old time are our assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat, for companies with 10 or more employees. Model cost: reading the order in our system (about €0.0006) plus matching the lines (Claude Sonnet 5.5, about 3,000 + 500 tokens), at the ECB rate of 1.1205 USD per euro on 22 October 2026.

See the full calculation →

This is how we implement it in companies

All case studies →

Client results.

All projects →
foap.comcustomer service

foap.com customer service: 95% of replies are sent automatically.

Users from several countries write to foap.com, in several languages. The system reads the entire conversation and the terms of that person, and then sends a response in that person's language. Questions about money and exceptions go to the team with a ready draft, so they have to check and send them.

the system sends the answers itself, without human typing
95%
time from the arrival of the e-mail to the ready response (median)
30 s
e-mails that require a response receive a ready-made draft
100%
less work for every 1000 answers (estimate)
47 h

Data from foap.com production, October 20-21, 2026. Estimate: 3 minutes for handwritten response.

How foap.com customer service works →
Sample messages. Money matters always come to the person.

Other implementations

jaktako.design

studio projektowe

−87%

Time to look for new customers, every day

4 hours → 30 min

approx. 73 hours less per month (21 days of work)

according to the studio

How the agent loop works →
Signature Estates

real estate

approx. −90%

Operator time spent browsing portals, per day

2–3 hours → 20 min

approx. 45 hours less per month (21 days of work)

respect · contact the seller 5 minutes after the announcement

How the agent finds property listings →
Kuba Koziej, CEO and co-founder of MoreGrowth and board member at Natu.Care

Kuba Koziej

CEO and co-founder, MoreGrowth

„We started with my own AI agent. During the training that followed, I learned to build new applications myself. Today I am bringing this way of working with AI into my business. Working with Syntalith gave me exactly the skills and tools I needed.”

View the original training review on LinkedIn ↗

This process can go on its own. You will check this on your cases before you pay.Book a free process review (30 min) →

How we build automation and agents

From a conversation to a working system in four steps.

  1. 01 · 30 min

    Free process review

    €0

    You're talking to an engineer. You receive the written plan within 2 business days.

  2. 02 · 5 days

    Free prototype

    €0

    The system works on 20-100 cases that your team has already handled. You see every result.

  3. 03 · 2–16 weeks

    Build

    50%

    Fixed price and goal written in the contract. First installment upon signing.

  4. 04 · after reaching the goal

    Reception

    50%

    You pay the second installment when the system reaches its target on your cases.

How a free prototype is created

Mon.

We set a goal

What result do you consider good?

Tue–Wed

The system is working

It goes through your affairs, one by one.

Thu

We compare

We check every difference with the team's work.

Fri

Result and price

List of errors and fixed implementation price.

You choose the matters. We anonymize them upon request, they stay in the EU and we delete them after the test.

On the market, such a test usually costs from PLN 3,000 to PLN 8,000.

Book a free process review (30 min)

We establish a prototype during a free analysis.

Data checked on October 21, 2026.

„Is my data safe?”

Yes. You choose where they go: from your company account to the model on your server.

  1. 00Employee's private account

    Customer and company data ends up in an account that the company cannot see or control. There is no data processing agreement, so it is a violation of the GDPR. When an employee leaves, the chat history goes with them.

  2. 01ChatGPT or Claude corporate account

    The provider does not use your data to train models. A copy of the queries remains in his logs for up to 30 days.

  3. 02API with zero retention (ZDR)

    The provider processes the request and does not save anything. It requires his consent, we prepare the application together.

  4. 03Processing in the EU

    Queries are counted and stored in Europe: OpenAI in the EU region, Claude via clouds with the EU region.

  5. 04Model at your place

    The open model runs on your server or in your cloud in the EU. The data does not go outside the company.

What we do with every implementation

  • Confidentiality agreement and data processing agreement before we receive any data.
  • You choose the cases for the prototype and we anonymize them upon request.
  • The data stays in the EU and we delete it after the test.
  • Corporate accounts with an administrator on your side.

When data cannot leave the company

The open model runs on your server or in your cloud in the EU. To choose from:

White-tailed eagle
Polish model, SpeakLeash and ACK Cyfronet AGH
PLLUM
Polish model, HIVE consortium commissioned by the Ministry of Digitization
Qwen
Alibaba
GLM
Zhipu AI
DeepSeek
DeepSeek

We select a model for the task and check it on your cases. We run it, tune it and maintain it.

Source: Bielik and PLLuM, ACK Cyfronet AGH ↗ · PLLuM, Ministry of Digitization ↗

Do you have a lot of your own data? We will fine-tune the small model.

  1. 1 Your examples
  2. 2 tuning
  3. 3 test on new cases
  4. 4 model at your place

When you have thousands of similar emails, documents or reports, we teach a small open model based on your examples. It works for you, responds quickly and costs less to maintain than a large model. We measure quality on issues that the model has not seen while learning.

Przemysław and Piotr did it in large programming and consulting companies. Artem did it before and does it today at Syntalith. It's about models on your own infrastructure, tuning and quality measurement.

You choose the protection level during the interview. We sign the data processing agreement before we see any data.Schedule a free analysis →

AI automations

This process can go on its own. You will check this on your cases before you pay.

The system takes over repetitive work from emails, documents and spreadsheets, and hands over uncertain matters to a human. A prototype for 20-100 cases that your team has already handled costs €0. You pay the other half of the price when the system reaches your goal.

See AI automations →
net for the automation of one process, paid once
from €3,000
from signing the contract to acceptance
2–6 weeks
free prototype on your cases
€0

Questions

  • What is UCP?

    The Universal Commerce Protocol, an open standard from Google and Shopify for purchases by AI agents. The store publishes a profile with the features it supports, and the agent uses it to run product discovery, the basket and checkout.

  • Does UCP work in the EU?

    According to Google, buying through UCP in AI Mode and Gemini today covers eligible products in the US, Canada and Australia, for selected merchants. A store in the EU can prepare its product data and measure traffic from assistants.

  • Who is the party to the transaction in a UCP purchase?

    The merchant. According to Google it remains the seller of record, and the buyer pays through Google Pay with details saved in Google Wallet.

  • How much does preparing a store cost?

    At Syntalith an audit of product data and readiness for agents costs from €600 net. Your own interface for agents, for example an MCP server with the catalogue, costs from €3,000 net.

Let's talk

Just write, call or choose a date.

We work fast because we hate corporate cotton wool. We don't have salespeople or managers to keep an eye on managers. You talk immediately to engineers who then build your system. We respect each other's time and yours too.

We will accept 3 more companies by the end of the year.

Mon–Fri 9:00–17:00 CET

What our OpenAI and Anthropic partnerships mean for you.

OpenAI makes ChatGPT and Anthropic makes Claude. We belong to the partnership programs of both companies, so we work with their tools every day and learn from the creators themselves.

OpenAI Select PartnerClaude Partner Network
01We will select a tool for the task
We implement both ChatGPT and Claude. We check both on your documents, and you choose the one that makes fewer corrections and saves more time.
02Knowledge straight from the creators
We learn from official OpenAI and Anthropic courses and materials. Your team learns about the features and settings that work today.
03Licenses without our margin
You buy accounts directly from OpenAI or Anthropic and receive an invoice from them. We do not add anything to the license.
04Certified engineers
On the team, we have an AWS certification in machine learning and an Anthropic certification in systems architecture on Claude.

Participation in programs does not mean that OpenAI or Anthropic endorses our services.