Inside AMEX’s agentic commerce stack: How intent contracts and single-use tokens enforce AI transactions

Source: VentureBeat

Overview

American Express (Amex) is building a system that lets AI agents shop and pay on behalf of users — but right now it’s only within its own payment network, and it still involves a black box that could hinder trust and auditability.

Amex already participates in agentic commerce protocol projects, especially Google’s Agent Pay Protocol (AP2) (VentureBeat), which focuses on interoperability. Amex’s Agentic Commerce Experiences (ACE) developer kit, on the other hand, touches on something most protocols currently lack: full transaction control in the payment layer.

ACE uses a closed‑loop system — serving as both the card issuer and the payment network — to validate agent‑led transactions.

“Some of what is missing so far is the perspective of a company like ours: We feel that trust and security are critical to advancing this space,” said Luke Gebb, Amex EVP and global head of innovation. “This is really the first time that an issuer is coming to the table.”

Amex occupies an interesting niche: unlike other financial institutions or card providers such as Chase or Bank of America, Amex can route transactions through its own American Express Network. Visa and Mastercard, by contrast, do not issue cards themselves and must work with a bank.

The continued black box of agentic commerce

The ACE kit is one approach to addressing some of agentic commerce’s biggest problems: trust, control, accountability, validation, and security.

• Consumers generally don’t want rogue agents to run away with their bank accounts and start buying things.
• Merchants don’t want to be stuck with unpaid items.
• Banks don’t want to deal with an influx of chargebacks and the potential for fraud.

Projects like the ACE kit aim to build trust and accountability by verifying an agent’s identity and goals, thereby creating the trust that agentic commerce desperately needs.

Amex claims it offers validation, but the process behind that is unclear. It abstracts how validation is performed, even though it explains at which layer it occurs. Traditional systems combine deterministic checks with flexible, semantic evaluation to match intent and outcome for validation. Amex says agents built with ACE can submit user shopping carts and check them against the agent’s original intent, but it does not disclose how this works.

Practitioners building for the agentic commerce ecosystem lament that, despite strides in creating a trust layer, many black boxes remain that could hinder widespread adoption.

Raj Ananthanpillai, founder and CEO of identity‑verification provider Trua, told VentureBeat that payment protocols and software kits like Stripe’s Agentic Commerce Suite, Google’s Verifiable Intent proof chain, and the ACE developer kit “excel at handling proofs, verifiable authorizations and the mechanics of fund movement, but leave upstream human validation opaque and underdeveloped.”

“Without a clear, high‑assurance cryptographic link proving that an agent is acting under the explicit authority of a verified human owner, merchants, issuers, and networks face heightened risks of repudiation, massive chargebacks, sanctioned people conducting financial transactions, and fraud,” he added.

The ACE kit

The ACE developer kit solves several recurring issues with agentic commerce and gives developers access to integrated services:

• Agent registration – establishes identity and trust with both the consumer and company agents.
• Account enablement – links the user’s Amex account to their agent and grants permission to act.
• Intent intelligence – creates an intent contract where the user defines what they want the agent to do. The system generates an Intent ID and a Proof of Intent Token that definitively proves authorization in the event of a dispute.
• Payment credentials – provides a single‑use token bound to the intent and its constraints for the actual transaction.
• Cart context – allows banks and brands to compare a user’s cart submitted by the agent to the original intent for validation.

When a transaction begins, the customer’s agent and the merchant’s agent can verify each other’s identities and trust that they are dealing with the correct entity.

“Once the agent has found the item that the customer has asked for, like red shoes, they’ll make a call for the payment credentials, which is a token that has the boundaries that the card member has provided,” Gebb explained. “So, for instance, if they said they only wanted to spend $500, that token won’t allow a purchase of $600 because it has controls built in.”

Amex’s approach shows that for agentic commerce to truly soar, providers must understand what systems will allow agents to act and who is ultimately accountable if something goes wrong.