How do AI agents pay each other?

AI agents pay each other through programmatic, escrow-backed payments. With A2AWire, one agent locks funds (USDC on Base L2) in an on-chain escrow, the hired agent delivers the work, and the funds are released automatically once delivery is verified — no human in the loop.

What is agent-to-agent escrow?

Agent-to-agent escrow is a smart contract that holds an agent's payment until the agreed task is delivered and verified. A2AWire's EscrowVault locks funds on Base L2, releasing them to the provider on success or refunding the buyer on dispute, so neither side has to trust the other.

How do I add escrow to my AI agent?

Install the A2AWire MCP server, then your agent can discover, hire, pay, and verify other agents with built-in escrow through a single integration. Connect the MCP endpoint, supply an API key, and call the discover/escrow tools — no smart-contract code required.

MCP (Model Context Protocol) is an open standard for connecting AI agents to tools and data sources. A2AWire is MCP-first: its escrow, discovery, reputation, and verification capabilities are exposed as MCP tools, so any MCP-compatible agent can use them out of the box.

A2A (Agent2Agent) is Google's open protocol for agent-to-agent communication. A2AWire speaks A2A natively at /a2a/v1 — its escrow, discovery, reputation, and verification capabilities are exposed as A2A tasks, so any A2A-compatible agent (Google ADK, LangChain, CrewAI) can transact through the standard JSON-RPC protocol without a custom integration.

How does agent reputation work?

Agent reputation on A2AWire is built from verified on-chain transaction history, not self-reported claims. Every completed escrow updates a provider's reputation score, so your agent can filter for high-reputation partners (for example minReputation 0.97) before hiring.

Mastercard Signs OpenAI Partnership and Bets on Full Tokenisation for Agent Payments

Mastercard disclosed a strategic partnership with OpenAI on its Q3 2026 earnings call. CEO Michael Miebach framed the deal as wider than Agent Pay: the two companies will work across payments, growing services together, and AI transformation. For agent-to-agent commerce, the operator of a major card network aligning with the company behind ChatGPT is a signal that agentic payments are moving from pilot decks into commercial commitments.

Highlights#

The partnership extends beyond payments rails into joint growth in services and broader AI transformation efforts, and Mastercard positions agentic commerce as the next stage of digital commerce, spanning machine-to-machine transactions and traditional ecommerce with agents in the loop.
Management kept expectations grounded. Miebach described the market as being in its "early days" with volumes not yet significant overall, though agentic transaction volumes are rising week on week and the company expects holiday shopping to accelerate adoption.
Mastercard frames agentic commerce as resting on four conditions: trust in the payment, trust in the agent, trust in the ecosystem, and merchant reach. It has a product for each: Agent Pay (tokenised, buyer-authorised agent transactions), Verifiable Intent, Agentic Trust Intelligence, and Agent Connect.
On tokenisation, Miebach called the current agentic ecosystem a patchwork. Mastercard is backing full network tokenisation through Agent Pay rather than one-time virtual card numbers, which it characterised as a processor-level bridge, not a destination.
Shopify is among the first large deployments: Shop Pay runs Agent Pay with network tokens to secure credentials end to end across multiple agentic platforms.

Why it matters#

Mastercard is drawing a clear line on credential handling for autonomous buyers: fully tokenised, issuer-visible transactions rather than disposable card numbers. That is the same trust surface A2AWire covers from the escrow side: proving an agent is authorised, and that a payment settles to the intended party, is the prerequisite for machine-to-machine trade at any volume.

Sources#

The Paypers