News
The Gist
- Open standard for agentic payments. Google unveiled the Agent Payments Protocol (AP2), an open spec to let AI agents make secure, auditable purchases.
- Trust via “mandates." AP2 uses cryptographically signed, verifiable mandates to prove user intent, authorization and accountability.
- Broad industry backing. More than 60 payments and tech partners—including Adobe, Mastercard, PayPal and Coinbase—are collaborating on AP2.
Google announced the Agent Payments Protocol (AP2), an open standard to help AI agents initiate and complete purchases across platforms with clear proof of user authorization and intent. AP2 extends Google’s earlier Agent2Agent (A2A) and builds alongside the Model Context Protocol (MCP) so agents can interoperate and transact across diverse systems.
Why this is notable now: Google says AP2 directly addresses three hard problems for agentic commerce—authorization, authenticity and accountability—using tamper-proof, cryptographically signed “mandates” that document a user’s instructions and purchase approvals. Early ecosystem support spans card networks, processors, fintechs and enterprise vendors, signaling a push to avoid a fractured, one-off approach to agent payments.
Table of Contents
- How AP2 Works
- Who’s In the Room
- Why Adobe Cares About Customer Trust
- From Agents Talking to Agents… to Agents Paying
- Industry Adoption Accelerates
- Technical Integration Framework
- What It Means for CX & Commerce Leaders
- Who Is Google?
- Who Is Adobe?
- FAQ: AI Agents and AP2
How AP2 Works
AP2 introduces Intent Mandates (capturing the user’s request, constraints and rules) and Cart Mandates (locking specific items, price and terms). Each mandate is a verifiable credential that creates an auditable chain from request to checkout—supporting cards, real-time bank transfers and stablecoins.
What AP2 Addresses
The AP2 framework is designed to tackle three core challenges in agent-led transactions.
| Challenge | What AP2 Provides |
|---|---|
| Authorization | Mandates proving an agent had specific authority for a purchase |
| Authenticity | Assurance that an agent’s request reflects the user’s true intent |
| Accountability | Clear audit trail if a transaction is incorrect or disputed |
Who’s In the Room
Google cites collaboration with 60+ organizations including Mastercard, American Express, PayPal, Coinbase, Etsy, Salesforce, ServiceNow, Worldpay and more. Separate partner posts (e.g., Ant International) also reference AP2 as a foundation for agent-led purchases.
Why Adobe Cares About Customer Trust
Adobe’s Loni Stark highlighted the importance of trust for AI-driven commerce and pointed in a LinkedIn post to Adobe’s work on the Content Authenticity Initiative (CAI). CAI recently crossed 5,000 members, highlighting industry momentum around verifiable content—the same kind of provenance and authenticity signals AP2 brings to transactions.
“With Adobe Commerce and AI agents powering customer journeys, we are focused on delivering secure, reliable, and authentic transactions for businesses and consumers," said Stark, VP of strategy & product at Adobe. "AP2 extends this value of verifiable trust into the experience layer of commerce, ensuring every AI-powered journey can end in an authentic, secure transaction. By standardizing how agents handle transactions, AP2 helps prevent the fragmentation of agentic commerce and creates a common foundation for all participants. Together with Google, we are shaping the standards and collaborations that will define the next era of digital commerce. We believe this ecosystem approach of open standards, trusted experiences, and interoperable platforms is the path forward for all building the future of AI-driven commerce."
Related Article: Building Customer Trust — Statistics in the US for 2025
From Agents Talking to Agents… to Agents Paying
AP2 builds on a year of groundwork to make agents interoperable (A2A) and better-connected to enterprise systems (MCP). Analysts and trade press framed AP2 as Google’s bid to make agent shopping trustworthy enough for mainstream commerce.
Industry Adoption Accelerates
The development reflects broader momentum in agentic AI commerce. Payment networks including Visa and Mastercard have begun enabling tokenized payments for AI agents, allowing automated purchases without exposing sensitive financial data.
These systems let customers set spending limits and review audit trails while maintaining oversight of agent transactions. The shift requires brands to for intent-driven, agent-initiated discovery and purchasing processes.
Technical Integration Framework
Protocols like MCP and AP2 aim to enable AI agents to connect with business tools, automate workflows and execute transactions with built-in transparency and governance features, Google asserts.
The framework is designed to streamline purchasing processes while ensuring accountability and compliance in autonomous digital marketplaces, according to the company.
Key Capabilities
- Secure transaction initiation across platforms
- User authorization verification
- Cross-system agent interoperability
- Tokenized payment processing
- Audit trail generation
- Spending limit controls
The protocol represents Google's effort to establish standards for AI-driven commerce as autonomous agents become more prevalent in digital transactions.
What It Means for CX & Commerce Leaders
- Standardization over bespoke builds. AP2 offers a common “rules of the road” so your agents don’t require one-off payment integrations per channel or method.
- Design for verifiability. Treat mandates as customer-facing artifacts (e.g., mandate receipts) to reduce disputes and build confidence in AI assistance.
- Road-test high-intent journeys first. Start with contained scenarios (drop alerts, back-in-stock, price caps) where mandates shine and risk is bounded, then expand.
- Mind the identity stack. AP2 presumes sound identity, consent, and data governance—align with your MCP/A2A agent architecture and payment risk controls.
Related Article: Customer Journey Mapping: A How-to Guide
Who Is Google?
Google Cloud spearheads AP2 as part of a broader push on interoperable agents (A2A) and context standards (MCP) to reduce fragmentation as agents become first-class actors in digital experiences.
Webinar
Sep
25
CMS Briefing: A Live Look at What’s Next in AI-Driven Platforms
Learn how leading organizations are using AI‑driven tools to publish faster, personalize smarter and stay secure.
Register
Webinar
Sep
25
Call Spoofing Trends Financial Institutions Can't Afford to Ignore
Don't let robocalls sabotage your customer relationships. Learn how to secure your voice channel.
Register
Webinar
Oct
15
Agentic AI Playbook Real-World Customer Service Use Cases You Can Deploy Now
Boost self-service by 30% and slash call volume by 63% with agentic AI.
Register
Webinar
On demand
Ready or Not: How Data-First Organizations Are Unlocking Agentforce Potential
Learn how to cut through the noise, activate Agentforce and build a Salesforce AI strategy that actually delivers.
Watch Now
Webinar
On demand
CX Reality Check: What Your Customers Are Really Thinking
Register now and get the insights you need to not just meet rising expectations, but exceed them.
Watch Now
Webinar
On demand
Content Leaders Collective: What a Good CCMS Actually Looks Like
Discover how content leaders transform clunky systems into growth engines — and why your competitors are ahead.
Watch Now
Who Is Adobe?
Adobe founded the Content Authenticity Initiative in 2019 to bring cryptographic provenance (Content Credentials) to digital media; CAI has surpassed 5,000 members. Adobe positions AP2 as a natural extension of trust—from content provenance to transaction provenance.
FAQ: AI Agents and AP2
Editor's note: Key questions on how AP2 and related protocols are shaping secure, agent-driven commerce.
Have a tip to share with our editorial team? Drop us a line:
