
Share
Google's new Agent Payments Protocol addresses security concerns in AI-driven transactions, offering a standardized approach to authenticate and validate payments conducted by intelligent agents across different platforms.
Today, Google announced the Agent Payments Protocol (AP2), an open protocol developed in collaboration with leading payments and technology companies. This new protocol aims to securely initiate and transact agent-led payments across various platforms, extending the capabilities of existing protocols like Agent2Agent (A2A) and Model Context Protocol (MCP).
With the rise of AI agents capable of transacting on behalf of users, a common foundation for secure authentication, validation, and authority conveyance becomes crucial. Traditional payment systems assume that a human is directly interacting with a trusted interface, but autonomous agents break this assumption by initiating payments independently. This shift raises several critical questions:
AP2 addresses these issues by providing a standardized, secure framework for transactions between agents and merchants. This helps prevent fragmentation in the ecosystem and ensures a consistent, reliable experience for users, merchants, and financial institutions.
The core of AP2 lies in establishing trust through mandates and verifiable credentials. Here’s a breakdown of how it works:

Google has partnered with over 60 organizations to develop and promote AP2. These include major players such as Adyen, American Express, Ant International, Coinbase, Etsy, Forter, Intuit, JCB, Mastercard, Mysten Labs, PayPal, Revolut, Salesforce, ServiceNow, UnionPay International, Worldpay, and more. This broad collaboration ensures that the protocol meets the diverse needs of the industry and is widely adopted.
AP2 opens up a range of possibilities for AI-driven commerce:
The Agent Payments Protocol (AP2) represents a significant step forward in the world of AI commerce. By providing a secure, standardized framework for agent-led transactions, AP2 helps bridge the gap between human and machine interactions, ensuring that users can transact with confidence across various platforms.
Tags
Original Sources
About the author
Kai built ML infrastructure at a Bay Area startup before developing an obsession with transformer architectures and inference optimisation that eventually pulled him out of product work entirely. A stint at a compute research lab sharpened his instinct for what actually matters in a model release versus what is marketing. He writes from the inside — from the perspective of someone who has debugged the systems he is describing at three in the morning. He is allergic to hype and instinctively drawn to the unglamorous plumbing questions that everyone else skips over.
More from The Engineer →This Week's Edition
18 September 2025
88 articles
Related Articles

OpenEvidence Targets Hospitals to Expand Its AI Chatbot for Doctors
Products & Applications · 3 min

OpenEvidence Launches Voice AI to Enhance Physician Workflow
Products & Applications · 3 min

Doximity Accelerates AI Investment in 2026, Targeting Multibillion-Dollar Market
Products & Applications · 3 min
Related Articles

OpenEvidence Targets Hospitals to Expand Its AI Chatbot for Doctors
Products & Applications · 3 min

OpenEvidence Launches Voice AI to Enhance Physician Workflow
Products & Applications · 3 min

Doximity Accelerates AI Investment in 2026, Targeting Multibillion-Dollar Market
Products & Applications · 3 min
More Stories