Agentic Commerce Shop

Finding and comparing products is the easy half of agentic commerce. The hard half is paying: how does a merchant know that an AI agent really has permission to spend someone's money, and how much? Several open efforts started in 2024 and 2025 to answer that. Here they are in brief, with what they mean for a store like this one.

The problem to solve

Online payments were designed around a person typing card details and clicking "pay". When software clicks instead, three questions need clear answers: who authorised the purchase, what exactly did they authorise, and who is responsible if something goes wrong.

The open efforts, in brief

• Model Context Protocol (MCP), published as open source by Anthropic in 2024, is a standard way for AI assistants to connect to tools and data. It is not a payment protocol, but it is one of the common ways agents reach the services they use.
• Agentic Commerce Protocol (ACP), released as open source by OpenAI and Stripe in 2025, lets an agent and a merchant complete a checkout together while the merchant keeps its own payment processing and its relationship with the customer.
• Agent Payments Protocol (AP2), announced by Google in 2025, uses signed "mandates", a record of what the person asked for and approved, so a purchase can be traced back to the person's intent.
• Visa Intelligent Commerce and Mastercard Agent Pay, announced by the card networks in 2025, are programmes for card credentials issued to AI agents, so their purchases can be recognised and limited.

They overlap and are still developing. What they share is the idea that an agent should carry proof of what it is allowed to do, and that the merchant should still own the sale.

What a store needs today

Whichever approach wins, a merchant needs the same foundation: an accurate catalog agents can read, and a real checkout connected to an established payment provider. This store supports Stripe, Square, Clover, Authorize.Net, Elavon, PayPal Payflow and Open Edge, each with a sandbox mode for testing.

aCOMMERCE Shop does not claim to implement any of the protocols above. It demonstrates the groundwork they all depend on. Its payment gateway is being connected; until then checkout stops before payment and no order is taken.

The human stays in charge

All of these efforts keep a person at the centre: you decide which agent to use, set its limits, and approve the purchases that matter. A good agent asks before it buys. A good store makes the facts clear enough that you can check what the agent chose.

More on the basics in Agentic commerce, in plain words.

When you open a product page you see a photo, a price and a button. When an AI agent opens the same page, it looks for something you never see: a block of structured data that states the facts precisely. Here is what that block contains on this store, field by field.

The hidden part of the page

Every product page here includes a JSON-LD script, a small piece of data in the schema.org vocabulary. Search engines have read this vocabulary for years; AI agents read it for the same reason: it removes guesswork. This is the offer of a sample product (since removed) as the store published it on 10 October 2026:

{
  "@type": "Product",
  "name": "65W Three-Port USB Charger",
  "sku": "65W-Three-Port-USB-Charger",
  "offers": {
    "@type": "Offer",
    "price": 39,
    "priceCurrency": "USD",
    "availability": "https://schema.org/InStock",
    "itemCondition": "https://schema.org/NewCondition",
    "priceValidUntil": "2026-11-09"
  }
}

What each field tells an agent

• name and description: what the product is, in the store's own words.
• sku: the store's item ID, a stable reference that does not change when the wording does.
• price and priceCurrency: an exact number and an ISO currency code, so there is no confusion between "$39", "39.00" or "USD 39".
• availability: whether the item is in stock, as a schema.org value rather than a phrase.
• itemCondition: new, used or refurbished.
• priceValidUntil: how long the price holds. This store sets it 30 days ahead, so an agent can tell a fresh price from a stale one.

Why the details matter

An agent comparing three chargers across five stores needs the same facts in the same shape from each of them. If one store hides its price in an image or its stock status in a sentence, the agent either skips it or has to guess, and guessing is how agents make mistakes for their users.

One detail to know if you build agents: on this platform the description field currently carries the description's HTML markup (paragraph and list tags), so strip tags before showing it to a person.

See it for yourself

Open any product in the store, view the page source and search for application/ld+json. The full list of what an agent can read here is on the For AI agents page.

Agentic commerce is shopping done by software that acts for you. You tell an AI agent what you need, and it searches, compares and, if you allow it, buys, within the limits you set. This guide explains what that means for shoppers and for stores, and what this demonstrator shows.

From search box to request

Today most online shopping starts with a search: you type, you open tabs, you compare, you decide. With an agent, you start with a request instead, for example "a USB-C charger that can power my laptop and my phone, under $50". The agent does the opening and comparing, and comes back with a short list and the facts behind it.

The decision stays with you. You choose which agent to trust, how much it may spend, and which purchases need your final yes.

What an agent needs from a store

A person can look at a photo and read between the lines. An agent cannot guess safely, so a store has to give it four things:

• A way to be found: stable product addresses, a store page that links to them, a sitemap, and a plain summary such as llms.txt.
• Facts it can read: structured product data in a shared vocabulary. schema.org Product and Offer is the one search engines and AI systems already understand.
• Facts it can trust: data that matches the page a person sees, prices with a validity date, and honest stock information.
• A way to pay: a checkout that software can complete safely, through a payment provider.

What this demonstrator shows

aCOMMERCE Shop is a small, working store built to show this on an ordinary website. Each product page publishes its name, description, picture, SKU, price in US dollars, stock status and condition as structured data. The site has an llms.txt summary, and an AI concierge answers questions on every page.

The cart works, and checkout runs up to the payment step. The payment gateway is being connected; until it is, no order is taken. The For AI agents page lists exactly what an agent can read here.

Why it matters for small stores

Agents favour stores whose facts are clear. That plays to the strengths of a focused shop with accurate product information, as long as that information is published in a form software can read. The good news is that most of it comes from doing the basics well: a clean catalog, honest prices and a working checkout.

Read more in Agentic commerce, in plain words, or see what an agent can read on the For AI agents page.

A little preparation can make a technology purchase much easier to use-and much easier to resolve if something goes wrong. Whether you are ordering a physical item or a digital download, use this checklist to confirm compatibility, understand delivery details, and ask the right questions about returns before you buy.

Start with the device or software you already use

A product can look right on a listing and still be wrong for your setup. Before ordering an accessory, check the exact model of the device it will connect to, not just its brand. A laptop’s charging port, a tablet’s generation, and a monitor’s available inputs can all determine whether a purchase works. For cables and adapters, check both ends of the connection and the capability you need: a USB-C connector alone does not tell you whether a cable supports video output or the charging power your device requires.

Software calls for a different set of checks. Confirm the supported operating system and version, whether the license is for one user or multiple users, and whether it is a subscription or a one-time purchase. If you are buying for a workplace, find out whether the license permits business use and how it is activated. Keep the device model and relevant system details handy when asking the shop a question; specific information is more useful than saying an item needs to work with “a Windows laptop.”

Check delivery details before placing an online order

If you need an item for a trip, installation, or project deadline, do not treat an estimated arrival date as a guarantee. Check the shipping options and any processing information shown at checkout, then allow room for carrier delays. Confirm that the address is complete, including an apartment, suite, or building number. If a package will be delivered somewhere you cannot receive it personally, think about whether there is a secure place for it to be left.

For software, check how the product is delivered before you order. A physical package and a digital license create different expectations: one may require transit time, while the other may involve an email, account, or activation instructions. If the delivery method is unclear on a product listing, ask before purchasing rather than assuming access will be immediate.

Digital products need their own checks. Look for the exact file or format you will receive, its size, what it needs to run (for example a web browser) and whether it works without an internet connection. Every product listing on aCOMMERCE Shop names the format you receive and how it is delivered, so you can check these points before you buy.

Read the return terms for the particular item

Return conditions can differ between physical technology products and software. Before buying, look for the applicable return window, the required condition of the item, and whether original packaging, accessories, or proof of purchase must be included. Ask who pays return shipping, whether any category has different rules, and how a refund is issued. Do not assume that opening a package, activating a license, or downloading software leaves the same options available as an unopened purchase.

If you are buying a gift, timing matters. A recipient might not open it until weeks after you place the order. Confirm the return terms before purchasing and keep the order confirmation where you can find it. The same care applies to a business purchase that must be approved or installed by someone else: check compatibility and return conditions before the product changes hands.

Document problems promptly and clearly

When an order arrives, inspect the outside of the package and compare the contents with the order confirmation. Keep the box, inserts, and accessories until you know the item is correct and working. If something is missing, damaged, or different from what you ordered, contact the shop promptly with the order details and a concise description of the issue. Photos of the packaging, shipping label, and item can help establish what arrived.

If the issue is performance rather than shipping damage, note the exact device or operating system involved and the steps you took before the problem appeared. For example, “the adapter connects but the monitor shows no signal on a 2022 laptop running Windows 11” gives someone more to work with than “it doesn’t work.” Do not share passwords, full payment-card numbers, or software activation codes in a public message.

Know whether you need a return, support, or warranty help

A product that is incompatible with your setup, an item damaged in transit, and a device that develops a fault after use are different problems. The right next step may depend on the shop’s return terms, the product’s instructions, or any manufacturer warranty that applies. Describe what happened and when, rather than assuming every issue requires a return.

For software, check whether the problem is installation, account access, or a license that does not match your needs. Save your purchase confirmation and any error message, but avoid posting license credentials publicly. Having those details ready makes it easier to ask a focused question and understand the options available for that specific product.

Before your next purchase, confirm compatibility and read the shipping and return information provided for the item. If anything remains unclear, ask the seller before ordering; for aCOMMERCE Shop, use the Contact page.

A useful technology setup is not necessarily the one with the most products. It is the one whose parts work together, fit the way you work and remain manageable after the initial setup. Whether you are updating a home office or equipping a small team, a few checks before you buy can prevent duplicate subscriptions, incompatible hardware and unnecessary troubleshooting.

Start with the work, not the product list

Write down three tasks your current setup needs to handle better. For example, you might need to join video calls from a laptop, share files with two coworkers and back up project documents. Then note what gets in the way today: unreliable audio, files scattered across accounts or a computer with too few ports. This gives each potential purchase a job to do.

Separate requirements from preferences. A webcam that works with your operating system is a requirement; a particular color or finish may be a preference. If a new tool does not solve a named problem or replace one you already use, pause before adding it. This is especially helpful with software: a second task manager may create another place to check without making any task easier to finish.

Check how new hardware connects to what you own

Before choosing an accessory, identify the exact model and operating system of the computer or device it will connect to. Look at its available ports and the specifications for those ports. A USB-C connector alone does not guarantee that a laptop can send video to a monitor through it, provide enough power for an accessory or support every function of a dock.

Map the full connection rather than checking one product at a time. If you want to run a laptop, external display, keyboard and headset at a desk, note which device connects to which port and whether you need charging at the same time. Check the display’s input, the cable type and any dock requirements. For wireless accessories, confirm the supported connection method and whether your computer allows it. The manufacturer’s compatibility documentation is a better source than the appearance of a plug.

Make software fit your accounts and files

Software compatibility includes more than whether an app launches on your device. Check where your files will live, who needs access and how information moves between tools. If a team already keeps documents in a shared workspace, a new app should have a clear way to import, export or link those files. Test an export format before committing important records to a service.

Look closely at licensing terms, too. A product intended for one person may not cover a shared team account, and a subscription may charge per user rather than per organization. Confirm device limits, supported operating systems and whether essential features require a particular plan. If the tool will hold customer information, review its access controls, sharing settings and privacy documentation before uploading real data.

Plan for setup, security and upkeep

The purchase is only part of the cost of a working setup. Set aside time to install updates, connect accounts and test the tasks you identified at the start. For a new headset, that might mean making a test call in the meeting app you actually use. For backup software, it means restoring a test file-not just seeing a message that a backup completed.

Give ongoing maintenance an owner, even if that owner is you. Keep a record of purchase details, license renewals and the email address used to register each product. Turn on multifactor authentication for important accounts, use unique passwords and remove access when a teammate no longer needs it. These small administrative steps make a setup easier to support months later.

• Before buying: record device models, operating systems, ports and the task the new product must improve.
• Before subscribing: confirm the number of users, required features, file export options and renewal terms.
• After setup: run one realistic task from start to finish and document anything that did not work as expected.

Choose the smallest useful next step

You do not have to rebuild your entire setup at once. If poor call audio is the immediate problem, address that before replacing software that already works. If file sharing is the bottleneck, agree on one storage location and a naming convention before adding another collaboration tool. Changing one part at a time also makes it easier to tell whether the change helped.

When you are ready to compare options, write down your device details and a short description of the task. Start with the one connection, workflow or software requirement you need to get right, and use that as your basis for a confident purchase.

aCOMMERCE Shop sells a small, deliberate range of digital products: single-file software apps that open in a web browser, and a book in PDF. It is an online store only. The range is small on purpose, and every app is tested before it is listed. Here is what that testing covers, and how you can use the same checks on any store.

A small range, each item with a job

Each app here does one clear thing: plan a budget, track time and invoice it, log daily expenses, check a price before you pay, set a profitable price, organise tasks or keep a simple customer list. A small range means each listing can be checked properly, and each one can say plainly what it does and what it does not do.

Tested the way a buyer uses it

Before an app is listed, it is opened in a real browser window and used like a customer would use it: real typing and clicks, with fictional sample data. The test covers every feature the listing mentions, and the everyday mistakes people make, such as empty fields, unusual numbers and special characters.

• Offline: the app is started with the internet switched off, to find out exactly what still works.
• Your data: anything the app saves is reloaded, backed up, and restored in a fresh browser, to make sure nothing is lost or doubled.
• Screens: it is checked at phone width and on a computer screen.
• Privacy: every network request the app makes is listed, so the listing can say what, if anything, leaves your browser.

This testing finds real problems before a customer does, for example a printout that lost its main figure, or buttons that went blank without an internet connection. Those are fixed before the app goes on sale.

A listing that only says what was tested

Each app’s description is written from its test results. If a feature was not tested, it is not advertised. Limits are stated in the listing itself: what needs an internet connection, where your data is kept, and that the apps were tested in Google Chrome on a computer rather than on a real phone. Every product page also carries structured product data, the same facts in a form AI shopping agents can read, and it is checked as a visitor sees it.

Use the same checks anywhere

Whatever you buy and wherever you buy it, a few questions save trouble: What exactly will I receive, and in what format? What does it need to run? Does it work offline? Where is my data kept, and how do I back it up? If a listing does not answer these, ask before you pay. For this store, the Contact page is the place to ask.