Agentspay

Explainer

Visa Intelligent Commerce, Visa Agentic Commerce, and the Visa Trusted Agent Protocol

Almost everything written about Visa Intelligent Commerce is a retelling of the April 2025 announcement, when Visa said AI agents would be able to pay with a Visa credential. Three more things have shipped since, including an open agent-identity protocol built with Cloudflare that most coverage does not mention at all. This page is the current version, checked against Visa’s own developer documentation and newsroom in August 2026.

Agent Payments Console

Pick an agent

Payment intent

intent:

Policy evaluation

Human approval required

This spend is over your approval threshold. Approve it to issue a scoped card, or deny it.

Scoped virtual card issued

Agentspay

single-use

Wallet budget

spent of

Audit trail

In short

Visa Intelligent Commerce (VIC) is Visa’s portfolio for AI agent payments, and by August 2026 it is three separate things rather than one product. First, the VIC APIs and Intelligent Commerce Connect on the Visa Acceptance Platform, which enroll a consumer’s card, capture consent, bind a device with FIDO and Visa Payment Passkeys, and issue a scoped, merchant-specific token an agent can spend. Second, the Trusted Agent Protocol, announced October 14, 2025 and co-developed with Cloudflare, which uses RFC 9421 HTTP Message Signatures so a merchant can verify that a specific agent is acting for a specific consumer. Third, a Visa MCP Server and Visa Acceptance Agent Toolkit that expose those APIs to agent frameworks. All three are built for the accepting side of the transaction. None of them gives a company whose own agents are buying a cumulative budget, an approval threshold or a single audit trail across its agent fleet.

What is Visa Intelligent Commerce?

Visa describes it on its own product page as a strategic portfolio for the age of AI agents, covering agents, issuers, merchants and developers. The word portfolio is doing real work in that sentence and it is the thing most write-ups get wrong. Visa Intelligent Commerce is not one API you integrate. It is a set of capabilities that arrived at different times, sit in different places, and are aimed at different parties: credential issuance and controls for issuers and consumers, an acceptance integration for merchants, an identity protocol for anyone receiving agent traffic, and developer tooling that wraps the lot. If you are evaluating VIC, the first useful question is not "how do I integrate it" but "which of the four am I actually the buyer of", because the answers are genuinely different pieces of work.

How does Visa Intelligent Commerce work?

The model is delegation on top of tokenization, and it runs in four steps. A consumer enrolls a card and gives explicit consent for an agent to use it, including spending limits and the conditions the agent must respect. Visa binds that consent to a device and authenticates it using standards it already runs, specifically FIDO and Visa Payment Passkeys, so the grant is tied to a verified person rather than to a string in a config file. The agent then receives a Visa-tokenized credential that is specific to a merchant and constrained by the consumer’s mandate, so a token minted for one airline and one trip window is worthless anywhere else. At checkout the merchant receives that token like any other card-not-present transaction, with Visa handling agent verification at the network level. The important structural point is where each control lives: the limits belong to the consumer’s mandate and the issuer, and the verification belongs to the network. Neither of those is your finance team.

What is the Visa Trusted Agent Protocol?

The Trusted Agent Protocol, or TAP, is the piece that deserves far more attention than it gets. Visa introduced it on October 14, 2025, co-developed with Cloudflare, and published a reference implementation at github.com/visa/trusted-agent-protocol. It solves a problem that predates payment: a merchant receiving automated traffic cannot tell a legitimate shopping agent from a scraper or a card tester, so the safe default has been to block bots and lose the good ones with the bad. TAP adds cryptographic agent identity to the ordinary HTTPS request using the RFC 9421 HTTP Message Signatures standard, aligned with the Web Bot Auth work. The agent signs the request; the merchant or its CDN verifies the signature against a public key registry, which is the same verification Cloudflare and AWS WAF already perform for signed bots. Visa framed the goal as making sellers able to trust AI agents as much as they trust their best customers, and the launch list was broad for a network-led spec: Adyen, Ant International, Checkout.com, Coinbase, Cybersource, Elavon, Fiserv, Microsoft, Nuvei, Shopify, Stripe and Worldpay.

What is the difference between agent-browser-auth and agent-payer-auth?

This is the most consequential detail in the whole specification and it is almost never written about. TAP carries the agent’s intent in the tag field of the Signature-Input header, and there are two values. agent-browser-auth means the agent is reading: browsing product pages, comparing prices, assembling a cart, not committing to anything. agent-payer-auth means the consumer has authorized this agent to charge a specific amount at this merchant, and the request should be treated as a binding payment instruction. The signature itself carries @authority and @path, created and expires timestamps, a keyid, an alg, a nonce and that tag, which is what makes it non-replayable and locked to one merchant and one operation. Read that list again from the buying side. TAP tells the seller, with cryptographic certainty, that an agent has authority to pay. It tells the company that owns the agent nothing at all.

What is Visa Intelligent Commerce Connect?

Intelligent Commerce Connect is the acceptance-side expansion Visa announced in June 2026, delivered through the Visa Acceptance Platform. The pitch is one integration instead of many: merchants, agent builders and payment enablers plug in once and get payment initiation, tokenization, spend controls and authentication, with support for payments initiated through several competing agent protocols rather than only Visa’s own. That protocol breadth is the genuine differentiator and it is a strategic bet worth naming. Where some players are trying to make their standard the standard, Visa is trying to make the standards question irrelevant to the payment, so a merchant is not stranded if the protocol it picked loses. If you are choosing between an integration path that assumes one protocol wins and one that does not, that difference matters more than any feature list.

Is there a Visa Intelligent Commerce API?

Yes, and there are now two ways to reach it. The direct route is the VIC APIs on the Visa Developer Platform and the Visa Acceptance Developer Portal, covering card enrollment on behalf of a consumer, consent capture, spending limits, mandate management and device binding. The newer route is the Visa MCP Server, which Visa announced in September 2025 as a secure integration layer letting AI agents and large language models connect directly to Visa Intelligent Commerce APIs. Built on top of it is the Visa Acceptance Agent Toolkit, which lets developers and non-technical users trigger Visa Acceptance API actions such as invoicing and Pay By Link with plain-language commands and no code. Both shipped in pilot, initially as a self-hosted npm package for JavaScript, with Visa publishing starter code at github.com/visa/mcp. If you have integrated payments through the Model Context Protocol before, the shape will be familiar.

Is Visa agentic commerce live yet, or still a pilot?

It is real, it is small, and Visa has been unusually specific about the numbers. On December 18, 2025 Visa announced it had completed hundreds of secure agent-initiated transactions with ecosystem partners, and named which ones: Skyfire with Consumer Reports product recommendations, Nekuda with the Gensmo fashion app and a Price.com integration, PayOS with BeyondStyle and Jomashop, and Ramp on the B2B side. Visa put more than 100 partners in the collaboration, more than 30 building in the VIC sandbox, and more than 20 agents or enablers integrating. It also cited a 4,700% surge in AI-driven traffic to US retail sites over the preceding year and said 47% of US shoppers were already using AI for shopping tasks. Hundreds of transactions is a pilot, not a channel. But the direction of travel is not in doubt, and Visa’s own framing was that 2026 is when agents stop assisting a purchase and start completing it.

Visa Intelligent Commerce versus Mastercard Agent Pay

They rhyme more than they differ. Both networks launched their agentic programs in April 2025, both replace raw card numbers with scoped agentic tokens, and both shipped machine-to-machine capabilities in June 2026. The emphasis differs: Visa is selling one integration that speaks many protocols and reaches any Visa-accepting merchant, while Mastercard Agent Pay is selling agent-to-agent settlement across cards, bank accounts and stablecoins with a wide partner set. Neither is a walled garden and both intend to interoperate with the emerging protocol stack rather than replace it. If you are picking between them, the full breakdown lives on our Visa Intelligent Commerce vs Mastercard Agent Pay comparison, including settlement rails, first issuing banks and where each one stops.

What Visa Intelligent Commerce does not do

Everything Visa has built here points at the transaction and at the seller. That is not an oversight, it is the correct scope for a card network, but it leaves a specific hole for any company whose agents are the ones spending. A merchant-scoped token caps one credential at one seller. TAP proves one agent’s authority for one request. A consumer mandate constrains one person’s card. Not one of those knows that the agent presenting the token has already spent eleven thousand dollars this month across nine merchants, because nothing in the design keeps a running total across agents, merchants and rails. Nor does any of it pause a purchase for a human when an agent tries to renew a contract, buy compute far outside its normal pattern, or loops on a retry. Visa says as much implicitly by where it puts the controls: the spending limits it advertises belong to the consumer’s mandate and the issuer, not to your finance team’s policy. This is the same structural gap that sits in Google’s AP2, in ACP and in x402, and it exists because a rail is scoped to authorize transactions rather than to govern budgets.

Where a control plane fits alongside Visa Intelligent Commerce

None of this is an argument against using Visa. If your agents buy from ordinary merchants, the card rail is the one that already reaches them, and a scoped agentic token is a decisive upgrade on the shared corporate card most teams are quietly using today. The missing layer sits above the rail rather than beside it. Agentspay is rail-neutral, so the policy you write does not change when the payment moves between Visa, Mastercard or a stablecoin. Each agent gets its own funded wallet with a hard limit, which makes overspending structurally impossible rather than merely discouraged. Every intended purchase is checked against policy before a credential exists: per-transaction ceiling, budget over a window, merchant allowlist, velocity rules. Spend above your threshold pauses for human approval instead of completing and being discovered later. The agent then receives a scoped virtual card good for that one purchase, riding Visa rails underneath. And every decision, the policy that allowed it, the agent that asked and the person who approved it, lands in one immutable audit trail. Visa decides whether the transaction is authentic. The control plane decides whether it should have happened.

What to watch next

Three things worth tracking. Whether TAP adoption spreads beyond the launch partners, because an agent-identity protocol is only useful when enough merchants verify it, and Cloudflare sitting in front of a large share of the web makes that plausible in a way a network-only spec would not be. Whether Visa’s protocol neutrality in Intelligent Commerce Connect holds once one standard pulls ahead on volume. And whether anything in the VIC roadmap ever crosses to the buying side, because as of August 2026 every control Visa has shipped belongs to the consumer, the issuer or the merchant, and none of it belongs to the business whose agent fleet is generating the spend. We keep this page current as those move. For a wider view of the vendors in this space, see our comparison of AI agent payment platforms.

Whatever standard moves the money, Agentspay is the rail-neutral control plane that keeps it governed. See how it works and the control surfaces that enforce policy, approvals, and audit on every transaction.

The portfolio

What Visa Intelligent Commerce actually ships

Checked against Visa’s developer documentation and newsroom in August 2026. Four pieces, announced separately, aimed at different parties.

Component What it does Announced Who integrates it
Visa Intelligent Commerce APIs Card enrollment with consent, spending limits, mandates, device binding via FIDO and Payment Passkeys April 2025 Issuers and agent builders
Trusted Agent Protocol (TAP) Cryptographic agent identity over RFC 9421 HTTP Message Signatures October 14, 2025 Merchants, CDNs, acquirers
Visa MCP Server Secure layer connecting agents and LLMs directly to VIC APIs September 2025, pilot Developers
Visa Acceptance Agent Toolkit Plain-language triggers for Acceptance APIs such as invoicing and Pay By Link September 2025, pilot Developers and non-technical users
Intelligent Commerce Connect One acceptance integration supporting several competing agent protocols June 2026 Merchants and payment enablers

Read the header

The two Trusted Agent Protocol intent tags

TAP carries agent intent in the tag field of the Signature-Input header. The distinction decides how a merchant should treat the request.

Tag value What the agent is doing What the merchant should infer
agent-browser-auth Reading product pages, comparing prices, building a cart Legitimate automated traffic. Serve it rather than blocking it.
agent-payer-auth Consumer has authorized a charge of a specific amount at this merchant A binding payment instruction from a verified delegation.

Where the limits live

What each Visa piece controls, and what it leaves open

Each of these authorizes or authenticates one transaction. None keeps a cumulative total across your agents, merchants and rails.

Agentic token Trusted Agent Protocol Consumer mandate A control plane
Caps a single transaction Yes No Yes Yes
Restricts which merchant Yes, one seller per token Signature bound to one domain Partly Yes
Proves who the agent is No Yes No Yes
Cumulative budget per agent No No No Yes
Human approval above a threshold No No No Yes
One trail across card, stablecoin and API spend No No No Yes

Frequently asked

Questions people ask about Visa Intelligent Commerce

What is Visa Intelligent Commerce?

Visa Intelligent Commerce (VIC) is Visa’s portfolio for AI agent payments, first announced in April 2025. It lets a consumer enroll a card, set spending limits and delegate authority to an agent, which then receives a Visa-tokenized, merchant-specific credential to spend within those conditions. By August 2026 it also includes the Trusted Agent Protocol, a Visa MCP Server and Intelligent Commerce Connect.

What is the Visa Trusted Agent Protocol?

The Trusted Agent Protocol (TAP) is an open specification Visa introduced on October 14, 2025, co-developed with Cloudflare, that gives AI agents a verifiable cryptographic identity when they contact a merchant. It uses RFC 9421 HTTP Message Signatures so a merchant can confirm a request comes from a real agent acting for a real consumer, instead of blocking all automated traffic by default.

How does Visa Intelligent Commerce work?

A consumer enrolls a card and consents to an agent using it, with spending limits attached. Visa binds that consent to a device and authenticates it with FIDO and Visa Payment Passkeys. The agent then gets a tokenized, merchant-specific credential constrained by the mandate. At checkout the merchant processes it like a card-not-present transaction, with Visa verifying the agent at the network level.

What is Visa Intelligent Commerce Connect?

Intelligent Commerce Connect is the acceptance-side expansion Visa announced in June 2026 on the Visa Acceptance Platform. It gives merchants, agent builders and payment enablers a single integration covering payment initiation, tokenization, spend controls and authentication, and it accepts payments initiated through several competing agent protocols rather than only Visa’s own.

Is there a Visa Intelligent Commerce API?

Yes. The VIC APIs are published on the Visa Developer Platform and the Visa Acceptance Developer Portal, covering enrollment, consent, spending limits, mandates and device binding. Visa also ships an MCP Server that connects agents and LLMs directly to those APIs, plus a Visa Acceptance Agent Toolkit for plain-language calls, initially as a self-hosted npm package for JavaScript.

What is the difference between agent-browser-auth and agent-payer-auth?

They are the two intent tag values TAP carries in the Signature-Input header. agent-browser-auth marks a browse-only request, where the agent is reading pages or building a cart. agent-payer-auth marks a payment-intent request, where the consumer has authorized a charge of a specific amount at that merchant, so the request should be treated as a binding payment instruction.

Who are the Visa Intelligent Commerce partners?

Visa named Adyen, Ant International, Checkout.com, Coinbase, Cybersource, Elavon, Fiserv, Microsoft, Nuvei, Shopify, Stripe and Worldpay for the Trusted Agent Protocol. On December 18, 2025 it reported completed agent transactions with Skyfire, Nekuda, PayOS and Ramp, more than 100 partners collaborating, more than 30 building in the VIC sandbox and more than 20 agents or enablers integrating.

Does Visa Intelligent Commerce set spending limits for my AI agents?

Not for your business. The spending limits VIC advertises belong to the consumer mandate and the issuer, and they constrain one enrolled card. They do not give a company a per-agent budget across its fleet, an approval threshold, a merchant allowlist you control, or one audit trail spanning card, stablecoin and metered API spend. Those are buy-side policies a control plane has to enforce above the rail.

Is Visa Intelligent Commerce the same as Visa agentic commerce?

In practice yes. Visa agentic commerce is the general description of Visa enabling AI agents to transact, and Visa Intelligent Commerce is the named portfolio that delivers it, including the APIs, Intelligent Commerce Connect, the Trusted Agent Protocol and the MCP Server. If you see the two used interchangeably, they are pointing at the same programme.

Can AI agents pay with a Visa card today?

Yes, in production but at pilot scale. Visa confirmed hundreds of completed agent-initiated transactions as of December 18, 2025, with named partners including Skyfire, Nekuda, PayOS and Ramp. Visa’s own position is that 2026 is the year agents move from assisting a purchase to completing it, with pilots extending to Asia Pacific, Europe and Latin America.

Keep reading

More explainers

ServiceNow AI Control Tower

ServiceNow AI Control Tower

ServiceNow AI Control Tower is the most complete agent inventory and risk console a large US enterprise can buy, and it now reaches across AWS, Google Cloud and Azure. We read the schema ServiceNow ships to developers to answer the one question the rollout meeting always ends on: can it stop an agent from spending money? It cannot, and the reason is written into the data model.

Read

Gemini Enterprise

Gemini Enterprise

Google did something in August 2026 that the other agent platforms have not done: it shipped a hard monthly spend cap that genuinely stops usage instead of emailing you about it. That deserves credit, and it also moves the interesting question one step along. A cap that stops something is only as useful as the thing it is scoped to, so we went and measured what Google can actually point that cap at, in the API model Google publishes for anyone to read.

Read

Salesforce Agentforce

Salesforce Agentforce

Agentforce is the largest agent platform any US enterprise is likely to already own, and it moved to consumption billing, which means the meter now runs on what your agents do rather than on how many seats you bought. That raises a finance question the rollout deck rarely answers: when an Agentforce agent is loose in production, what actually stops it spending. We went and measured the answer in Salesforce own published object model rather than guessing at it.

Read

AWS AgentCore

AWS AgentCore

Amazon shipped the missing piece in August 2026. Bedrock AgentCore Payments went generally available, and it is a real payments product: an agent can now hold a wallet, meet an HTTP 402, pay, and carry on reasoning without a human in the loop. So the question a platform lead has to answer stopped being whether AWS gives agents money and became a narrower, more awkward one: how much of a spend policy did AWS actually ship? We went and measured it, property by property, in the API model AWS publishes.

Read

Microsoft Agent 365

Microsoft Agent 365

Microsoft shipped a control plane for AI agents, and it is a good one. It gives every agent an identity, a registry entry, an owner, a sponsor and a Conditional Access policy. Then somebody in finance asks the obvious follow-up question: fine, but what stops the agent from spending money? This page answers what Agent 365 costs, what it governs, and what we measured when we went looking for a dollar amount anywhere in Microsoft's agent governance surface.

Read

QuickBooks MCP Server

QuickBooks MCP server

Connecting an accounting system to an AI assistant is now a ten minute job. Deciding what that assistant is allowed to do once it is connected is the part nobody writes about, and it is the part your controller will ask about first. This page compares what the official QuickBooks, NetSuite and Xero MCP servers actually hand a model, measured rather than summarized from marketing pages.

Read

Payment MCP Servers

payment MCP servers

Every large payment company shipped an MCP server in the last eighteen months, and almost every write-up of them is a setup tutorial. The setup is the easy part. The question worth answering before you connect one to a production account is narrower and much less comfortable: what, exactly, can the model on the other end of that connection do to your money?

Read

PayPal Agentic Commerce

PayPal Agentic Commerce

PayPal made a bet that most merchants would rather not implement a commerce protocol at all. Where Stripe and OpenAI shipped a spec for you to build against, PayPal shipped two products that sit on top of the checkout you already have, and then bought a company to make the catalog half work. That choice is the whole story: it explains why Agent Ready needs almost no engineering from you, why there is nothing for an agent to discover about your store on the open web, and why the thing PayPal will not do for you is the thing that gets expensive later.

Read

Shopify Agentic Commerce

Shopify Agentic Commerce

Shopify switched agentic commerce on by default, so your store is probably already selling to AI assistants whether or not anyone on your team configured it. Instead of restating the announcement, we checked something you can check too: on September 2, 2026 we requested the machine-readable capability file that Shopify publishes for real storefronts, on fourteen well-known US brand domains, and read what it exposes to an agent. Eleven answered correctly. The three that did not share one trait, and it is quietly costing them agent traffic.

Read

Web Bot Auth

Web Bot Auth

Web Bot Auth is the reason your agent either gets served or gets throttled with the scrapers. Almost everything written about it repeats the same architecture diagram, so we did something different: on September 1, 2026 we fetched the published key directories of more than twenty major AI operators and infrastructure vendors to see who is genuinely signing their traffic. Four were. The results are in the first table.

Read

Tempo Blockchain

the Tempo blockchain

Tempo is the payments chain Stripe and Paradigm built, and it shipped with a protocol that lets software pay for things on its own. It settles machine payments in under a second. It has nothing at all to say about whether your agent should have paid.

Read

AI Agent Governance

AI agent governance

Every agentic AI governance framework published so far governs the same four things: identity, tools, data and prompts. Not one of them carries a budget. Here is what the real frameworks say, which guardrails actually bind at runtime, and what to do about the last mile none of them reach.

Read

A2A Protocol

A2A Protocol

Most explanations of the A2A protocol stop at the sentence that agents can now talk to each other. That was true in April 2025 and it is no longer the interesting part. A2A shipped version 1.0 in April 2026 under Linux Foundation governance, it runs in production inside Azure AI Foundry and Amazon Bedrock AgentCore, and the questions engineers actually get stuck on are narrower: what an Agent Card commits you to, when to reach for MCP instead, and what happens the first time one of your agents has to pay another one for the work. That last question has a specific answer, and it is not in the core spec.

Read

Mastercard Agent Pay

Mastercard Agent Pay

Nearly every article about Mastercard Agent Pay is a retelling of one press release from April 2025, the one where Mastercard said AI agents would be able to shop with Agentic Tokens and named Microsoft as the first platform. That was sixteen months ago, and four more things have shipped since. Reading only the launch coverage leaves you with roughly a quarter of the picture, and the missing three quarters are the parts that decide whether you can actually put this into production.

Read

Stripe agentic commerce

Stripe agentic commerce

Most writing about Stripe and agentic commerce is still a retelling of the September 2025 launch week, when Stripe and OpenAI shipped Instant Checkout and published the Agentic Commerce Protocol together. Stripe has built a good deal more since then, and some of it points in a direction the launch coverage never anticipated. This page is the current version, checked against Stripe’s own documentation in August 2026.

Read

ChatGPT Instant Checkout

ChatGPT Instant Checkout

Almost every guide to ChatGPT Instant Checkout still reads like it was written the week it launched, walking merchants through how to apply and what the fee will be. OpenAI changed course in March 2026. Here is the accurate version: what Instant Checkout was, what the numbers actually looked like, what replaced it, and which parts of the stack are still very much alive.

Read

Google AP2

Google AP2

Most guides to Google AP2 still describe an Intent Mandate and a Cart Mandate, because most of them are rewrites of the September 2025 launch post. The specification moved. Here is what the Agent Payments Protocol actually defines today, and the one question it deliberately does not answer.

Read

Human in the loop AI

Human in the Loop AI

Every guide to human in the loop AI describes the same shape: the agent pauses, a person decides, the agent continues. The shape is right. What almost none of them ask is a harder question, which is where the pause is enforced, because a pause written into the agent's own code is a pause the agent is trusted to honor.

Read

AI agent cost

AI Agent Cost

Every cost guide for AI agents answers the same two questions: what does it cost to build, and what does it cost to run. Both are answerable, and both are on somebody's invoice. The third question is the one that ends up in a variance report, because the agent also spends your money, and nobody sends you a bill for that.

Read

Agentic checkout

Agentic Checkout

Nearly every guide to agentic checkout is written for the merchant who wants to receive these orders. Far fewer are written for the company whose agents are placing them, which is odd, because agentic checkout quietly removes the one screen where spending used to get a second look.

Read

API monetization

API Monetization

Most guides to API monetization argue about which pricing model wins. The harder question in 2026 is who is calling. An API priced for a signed-up developer with a key behaves very differently when the caller is an agent that showed up once, wants one record, and has no account.

Read

x402 protocol

x402 Protocol

x402 took the one HTTP status code the web never used and turned it into a payment rail machines can drive. The protocol is elegant and genuinely small. The part it deliberately leaves to you is the budget.

Read

AI procurement agents

AI Procurement Agents

Every major procurement suite shipped agents during 2026. Almost none of them answer the question your controller will ask first, which is what happens when the agent is wrong about a purchase and the money has already moved.

Read

Agentic payments

Agentic Payments

Agentic payments move money with no human at the checkout. The rails to do it all shipped during 2026. The part most teams have not solved is deciding, before the money moves, whether the agent was allowed to spend it.

Read

AI agent monetization

AI Agent Monetization

Every AI agent company is rewriting its price list. The models that survive are metered. The ones that quietly fail are the ones where nobody measured what a single task costs to serve.

Read

Agent payment platforms

AI Agent Payment Platforms

Five different kinds of product now call themselves an AI agent payment platform, and they solve five different problems. Picking the wrong category is the expensive mistake, not picking the wrong vendor inside a category.

Read

Universal Commerce Protocol

the Universal Commerce Protocol (UCP)

Google and Shopify shipped UCP as an open standard so an AI agent can check out at any merchant that supports it. Here is what the specification actually defines, where it is live for US buyers, and the one thing it deliberately leaves to you.

Read

MCP Payments

MCP Payments

MCP payments are how an AI agent discovers a payment tool and calls it to move money. The catch: the Model Context Protocol carries the tool call, not the spending decision, so nothing in the stack asks whether the purchase should have happened.

Read

Visa Intelligent Commerce vs Mastercard Agent Pay

Visa Intelligent Commerce vs Mastercard Agent Pay

Visa Intelligent Commerce and Mastercard Agent Pay are the two big card networks racing to let AI agents pay. They take different routes to the same idea, and neither one decides whether a given purchase should have happened.

Read

Agentic Commerce Protocol

the Agentic Commerce Protocol

ACP is the open standard behind agentic checkout in ChatGPT. It tells a merchant how to sell to an AI agent. It says nothing about whether your agent should have made the purchase.

Read

AP2 vs ACP vs x402

AP2 vs ACP vs x402

AP2, ACP, and x402 are the three standards shaping how AI agents pay. They solve different layers of the problem, and most real systems will touch more than one.

Read

Machine payments protocol

Machine payments protocol

As software starts paying software, machine payments protocols define how value moves without a human at the keyboard. The harder question is how to keep that spending governed.

Read

Know Your Agent (KYA)

Know Your Agent

KYA, or Know Your Agent, extends the idea of customer due diligence to autonomous software. When an agent spends, you need to know which agent, on whose authority, and under what limits.

Read

Keep agent spending governed

Add policy, hard limits, human approval, and an immutable audit trail across any protocol or rail. Start in the sandbox today.

Never moves money without policy