AB
AiBoss
Wiki

What is AP2 (Agentic Payments Protocol)? - AI Encyclopedia

AP2 (Agentic Payments Protocol) is an open protocol that provides users with a secure, scalable, and payment-agnostic framework to enable smart agent payments across platforms for users, merchants, and payment providers.

AP2(Agentic Payments Protocol)是什么? - AI百科知识

AgentThe IC Payments Protocol (AP2) is an open protocol jointly launched by Google and more than 60 organizations, including Coinbase, to provide...AIacting(AI AgentAP2 provides a secure and interoperable framework for payment transactions initiated by AP2. Through cryptographically signed digital contracts, AP2 ensures the tamper-proof and auditable nature of transactions, supporting multiple payment methods including credit cards, debit cards, stablecoins, and real-time bank transfers. It ensures transaction traceability and the clarity of user intent through Intent Mandates and Verifiable Credentials. AP2 is not only suitable for consumer scenarios but will also play a vital role in enterprise business workflows, such as...automaticProcurement and Software LicensingautomaticExtend.

What is AP2?

AP2 (AgentThe IC Payments Protocol (ICP) is an open protocol that provides users with a secure, scalable, and payment-agnostic framework that enables users, merchants, and payment providers to conduct payments across platforms.intelligentbodyPayment. ForAIAgents provide a common foundation for users to conduct payment transactions, ensuring the security and compliance of transactions and preventing ecosystem fragmentation.

AP2 working principle

  • Mandates (Authorization Letter)This is a digitally signed contract, serving as verifiable proof of user instructions. Mandates come in two types:
    • Intent MandatePre-signed proxy operation constraints by the user apply to scenarios where the user is not present. For example, if a user tells the agent to "buy concert tickets as soon as they go on sale," this request is recorded in the Intent Mandate.
    • Cart MandateThis refers to the user's final approval of a specific shopping cart item (product, price, currency), applicable to scenarios where the user is present. For example, a user asks an agent to help find a pair of sneakers; after the agent finds them, the user confirms the purchase; this confirmation process generates a Cart Mandate.
    • User/Shopping Agent: Responsible for parsing user tasks and negotiating shopping carts, but does not handle payment credentials.
    • Credential ProviderManage payment methods (such as wallets) and store payment card numbers or tokens.
    • Merchant endpointProvides quotes and signs up shopping carts, but does not access the user's payment information.
    • Payment processorConstruct a network authorization request and receive a Payment Mandate.

    Through these mechanisms, AP2 ensures the security, transparency, and auditability of the transaction process, providing...AIPayment transactions in the era of agents provided a solid foundation of trust.

    AP2's main applications

    • intelligentShoppingUsers can allowAIThe agent monitors prices and inventory, and once conditions are met...automaticComplete the purchase. Users can express their needs for specific products to the agent, who will then communicate with the merchant to create a customized discount plan for the user.
    • Coordination tasksUsers can delegateAIAgents accomplish complex tasks, such as booking travel, and can coordinate with multiple service providers to complete multiple bookings simultaneously.
    • Decentralized Applications (DApps), Supply ChainautomaticScenarios such as digitalization and content delivery networksAP2 allowedintelligentbodyThe ability to initiate, verify, and complete payments independently under preset rules greatly improves the operational efficiency of these scenarios.
    • machine economy:AI AgentYou can charge for your services, or charge others.AgentPayment, on behalf of the userautomaticProcessing micropayments. Different platforms...AgentThey can communicate and collaborate with each other, possess genuine payment capabilities, and can independently complete transaction settlements. For example, in a demonstration of their collaboration with Lowe’s Innovation Lab,AIintelligentbodyCompleted a full shopping process: from diagnosing needs,recommendFrom sourcing goods and confirming the order to using USDC for payment and triggering the fulfillment process, all operations are handled by [the relevant authority/organization].AICompleted independently.
    • Support emerging payment systemsAP2 is designed as a universal protocol that supports emerging payment methods such as stablecoins and cryptocurrencies. For example, the A2A x402 extension, developed in partnership with Coinbase, provides a production-grade solution for proxy-based crypto payments.

    Challenges facing AP2

    • Technical aspects
      • Technological fragmentationThe rules of A2A systems vary from country to country. For example, Brazil's PIX system and Mexico's SPEI system lack a unified standard, making it difficult to scale up and apply across markets.
      • Reaction speed and cost:AIProxy task execution is time-consuming and costly. For example, booking a hotel using the ANP protocol may take 5-6 minutes and consumes a lot of context. If the cost cannot be reduced, it will hinder the implementation of the protocol.
      • Legal gapsThere are currently no clear regulations or provisions.AILiability for erroneous transactions by agents. In Mexico and Brazil, if a transaction is made using user credentials, the user is held responsible even if the error is due to the agent's mistake. Brazil is currently promoting...AIThe principle of system responsibility applies, but its application in the payment field is still in its early stages.
      • Defining responsibility is complexWhen fraud occurs, it is difficult to determine whether it is the user, merchant, bank, or...AIThe responsibility lies with the model itself.
      • Real-time payment risksA2A payments require real-time settlement, and fraud detection needs to be completed within milliseconds. More adaptable models and pre-transfer verification are needed, such as verifying the recipient's bank account to ensure the correct flow of funds.
      • AILack of transparency in decision-makingCurrent language models cannot explain the decision-making process. If funds are managed by an agent, it is necessary to ensure that the agent is accountable and to address issues such as how to audit the agent and avoid bias or unfair decision-making.
      • imperfect ecosystemWhile AP2 provides a basic trust layer, more tools and services are needed to realize agent business. For example, traditional payment platforms struggle to meet these requirements.AIThe company's flexible pricing model requires the construction of new infrastructure.
      • Market acceptanceDespite AP2's many advantages, the market's acceptance and adoption speed are uncertain, and more practical experience and case studies are needed to prove its value.

      AP2's Development Prospects

      • Technological integration and innovation
        • AISynergy with crypto financeAP2 isAIAgents provide economic action capabilities, and stablecoins and other crypto-financial instruments have become popular due to their characteristics.AIThe ideal choice for payment, which signifiesAIIntegration with crypto finance at the infrastructure layer is becoming a reality.
        • Cross-platform and cross-chain paymentsAP2, as an extension of the A2A and MCP protocols, supports multiple payment methods and will gradually develop into a cross-platform, cross-chain, and cross-industry platform.intelligentPayment ecosystem.
        • promoteAIBusiness ModelAP2 supportsAIAgents act as users' representatives in shopping and coordinating complex tasks, such as...automaticMonitoring prices and inventory, creating customized offers, coordinating travel bookings, etc., forAIThis provides the foundation for a business model driven by [the government/entity].
        • Expanding the machine economyAP2 enablesAIAgents can autonomously manage digital assets, collect fees, and make payments, driving the development of the machine economy, for example...AIService transactions and micropayments between agents.
        • Increased user acceptanceAs users...AIAs people become more familiar with agent payment methods, their impact on...AIThe acceptance of agents owning digital assets will gradually increase.
        • More Ecosystem PartnersAP2 has received support from more than 60 organizations, including payment platforms, financial institutions, and technology companies, and its ecosystem is constantly expanding.
        • Become the industry standardAP2, as an open protocol, aims to become...AIA universal standard for agent payments promotes interoperability between different platforms and ecosystems.
        • Promote the improvement of laws and regulationsAs AP2 develops, its practices in legal and liability definition will drive the improvement of relevant regulations, providing a basis for...AIProxy payment provides a clearer legal framework.
        • Enhance transaction securityAP2 ensures the tamper-proof and auditable nature of transactions through cryptographically signed digital contracts and verifiable credentials, providing users with a safe and reliable payment environment.
        • Building a foundation of trustBy adhering to the principle of "verifiable intent rather than inferred action," AP2 creates a complete chain of evidence from intent to shopping cart to payment, forming an irrefutable audit trail.

        What is the AGL framework? A comprehensive guide. AIEncyclopedic knowledge

        AgentWhat is Context Engineering (ACE)? AIEncyclopedic knowledge