Agentic commerce protocols, explained

Last verified: 9 August 2026

The problem these protocols solve

A customer tells an assistant to buy a specific lamp in brushed brass, ship it to the office, use the corporate card. For that to complete without a human touching a browser, six things have to happen:

The agent has to find your catalog. It has to understand the product — variants, stock, price, shipping. It has to build a cart and get an accurate total including tax and freight. You have to verify the agent is legitimate and acting for a real customer with real authority. Money has to move. And you need a record of what was agreed, in case it goes wrong.

Before 2025 there was no standard way to do any of this. Agents scraped pages, guessed at prices, and failed at checkout. The protocols below exist because scraping doesn't scale and merchants hated it.

This guide covers discovery through cart. The verification and money-movement half has its own guide — see Agent payment rails, explained. For the whole field at a glance, start with the agentic protocol landscape.

Two protocols, and they took different paths

Agentic Commerce Protocol (ACP)

OpenAI and Stripe launched ACP on 29 September 2025, the same day ChatGPT got Instant Checkout. Apache 2.0, date-versioned, currently at 2026-04-17.

The original pitch was complete: an agent inside ChatGPT could search products, build a cart, and pay — without the customer leaving the conversation. Etsy went live at launch with a million-plus US sellers. Walmart signed a partnership two weeks later.

Then in March 2026, OpenAI pulled native checkout out of ChatGPT. Their own explanation: "the initial version of Instant Checkout did not offer the level of flexibility that we aspire to provide."

What replaced it is a discovery model. Agents surface your products inside ChatGPT; you run your own checkout. The named discovery partners after the revamp — Target, Sephora, Nordstrom, Lowe's, Best Buy, The Home Depot, Wayfair — are all sending customers to their own storefronts. Walmart went further and built a dedicated ChatGPT app with account linking, loyalty, and Walmart's own payments.

That's not a failure. Discovery inside a surface with hundreds of millions of users is worth a great deal. But it is a materially different product than the one announced, and any strategy deck written before March 2026 has this wrong.

Universal Commerce Protocol (UCP)

Google announced UCP on 11 January 2026, co-developed with Shopify, Etsy, Wayfair, Target, and Walmart. Apache 2.0, currently at v2026-04-08.

UCP kept the full checkout scope that ACP retreated from, and it grew fast. On 24 April 2026 the Tech Council expanded to include Amazon, Meta, Microsoft, Salesforce, and Stripe — joining Google, Shopify, Etsy, Target, and Wayfair.

Read that list again. Amazon and Google on the same technical council. Microsoft too. And Stripe, which is a founding maintainer of ACP.

Beyond the Council, the endorser list runs through Adyen, American Express, Best Buy, Flipkart, Klarna, Macy's, Mastercard, PayPal, The Home Depot, Visa, and Zalando. UCP has also started extending into lodging — Marriott, Hilton, Booking.com, Expedia, Amadeus — and food ordering with DoorDash, Uber Eats, Square, and Toast.

Where this actually landed

No one announced a merger. But the pattern is hard to miss.

ACP moved away from checkout in March. UCP consolidated checkout backing in April. The one company with a foot in both camps — Stripe — joined the UCP council while remaining an ACP maintainer. Meta did the same thing.

Our read, and we'll say the confidence level plainly: we think UCP is where the transaction layer settles, at maybe 70% confidence. The remaining 30% is that ChatGPT's distribution is large enough that a discovery-only ACP still shapes how a lot of commerce starts, and that OpenAI takes another run at checkout with a different design.

What that means practically: these aren't an either/or. They now do different jobs. ACP is a demand channel. UCP is transaction infrastructure. A merchant with both is not hedging — they're covering two parts of the same funnel.

How UCP works, concretely

Discovery is a well-known file. You publish a manifest at /.well-known/ucp on your domain. An agent fetches it and learns what you support. If you've implemented robots.txt or llms.txt, the mental model is the same — a machine-readable statement of capability at a predictable path.

Capabilities are negotiated, not assumed. You declare what you can do — catalog browsing, cart operations, checkout, order status. An agent that needs something you don't offer knows before it tries. This is the part most merchants underestimate: you can adopt UCP for discovery and catalog only, and add checkout later, without breaking anything.

Extensions are namespaced by reverse domain. Vertical-specific or merchant-specific behavior doesn't pollute the core spec.

Transport is your choice. REST, or over A2A, or over MCP. If you've already built MCP infrastructure, that's not wasted work.

Payments hand off to AP2. UCP doesn't reinvent money movement. It's designed to work with the Agent Payments Protocol, which now lives at the FIDO Alliance.

What this asks of your product data

Here's the part that gets skipped, and it's the part that actually determines whether any of this works for you.

Agentic commerce is unforgiving about product data in a way that human browsing never was. A human sees "Brushed Brass — 3 left" and understands. An agent needs the finish as a structured attribute with a controlled value, the inventory as a number with a freshness guarantee, and the price as an amount with a currency and a validity window.

The failure modes we see most:

• Variants encoded in the title. "Modern Sconce - Brass - Large" is one product to an agent unless the variant axes are structured. It cannot filter on a substring it doesn't know is a filter.
• Inventory that's directionally true. Human shoppers tolerate a stale stock count. An agent that builds a cart against stale inventory produces a failed order and a customer who blames you, not the agent.
• Pricing that depends on context the agent can't see. Logged-in pricing, regional pricing, and cart-level promotions all need to be expressible in the protocol or the total will be wrong at the last step.
• Shipping estimated at checkout only. If freight isn't computable until the final step, the agent can't compare you against alternatives, and it will drop you earlier in the process than you'd like.

None of this is new advice. It's the same data hygiene that made feeds work for paid shopping. What's new is that the penalty moved from lower ad performance to the transaction does not complete.

What we'd do, in order

• 1. Fix the catalog before touching a protocol. Structured variants, controlled attribute values, real-time inventory, computable shipping. Every protocol on this page is a transport for this data. Bad data transported perfectly is still bad data.
• 2. Publish the UCP manifest. Discovery and catalog capability only. This is a small piece of work and it makes you visible to the layer that's consolidating.
• 3. Get into ACP discovery. Different audience, different surface, low incremental cost once the catalog is clean.
• 4. Decide on checkout deliberately. Whether an agent completes a purchase without touching your storefront is a business decision about margin, attribution, and customer relationship — not a technical one. Walmart looked at it and built their own app instead. That was a strategy call, and it was probably right for them.
• 5. Put a re-check on the calendar. Ninety days. This layer moved three times in the last twelve months.

Questions worth asking a vendor

If someone is selling you agentic commerce readiness, these separate the real from the deck:

• Which spec version have you implemented, and when did you last update it?
• Does our UCP manifest declare checkout capability, or only discovery? Which do you recommend and why?
• How does inventory freshness get guaranteed between our system and the manifest?
• What happens to attribution when the purchase originates in an agent?
• If ACP changes again, what breaks?

The last one matters most. Anything built as a one-time integration against a moving standard is a liability with a delivery date.

Sources

ucp.dev · Universal Commerce Protocol on GitHub · Google: agentic commerce and UCP · Shopify Engineering: Building UCP · Agentic Commerce Protocol · ACP on GitHub · OpenAI: Buy it in ChatGPT · Forrester on the ACP pullback · UCP Tech Council expansion