The agentic commerce protocol landscape is not converging on a single winner. It is forming a layered stack where different protocols own different functions.
| Dimension | Traditional UX | Agentic Experience Design (AXD) |
|---|---|---|
| Primary material | Attention and affordance | Trust and delegation |
| User state | Present, navigating | Absent, delegating |
| Design output | Screens and interfaces | Outcomes and constraints |
| Temporal model | Session-based | Relationship-based |
| Success metric | Task completion | Trust calibration |
Agentic Experience Design (AXD) is the discipline for designing trust-governed relationships between humans and autonomous AI systems that act on their behalf.
Agentic commerce is the practice of autonomous AI agents transacting, negotiating, and purchasing on behalf of humans in markets without direct human involvement.
Tony Wood, an Emerging Technologies and Innovation Consultant based in Manchester, United Kingdom, founded AXD in September 2024.
In March 2026, Google published a developer's guide that quietly settled one of the most consequential questions in This essay argues that the protocol landscape is not converging on a single winner. It is converging on a Twelve months ago, the agentic commerce protocol landscape did not exist. MCP had been released by Anthropic in November 2024, but it addressed tool connectivity, not commerce. Google's A2A followed in April 2025, solving agent-to-agent communication. Neither was designed for the specific challenge of an AI agent purchasing goods on behalf of a human. The commerce-specific protocols arrived in rapid succession. Google and Shopify announced the The internet did not converge on a single protocol. It converged on a stack: TCP/IP for transport, HTTP for application, TLS for security, DNS for naming. Each layer solved a different problem. Competition existed within layers — HTTP vs Gopher, SSL vs TLS — but the architecture was always layered. The agentic commerce protocol landscape is following the same pattern. Google's developer guide makes this explicit. The six protocols it describes map to three functional stages: The AXD Institute identifies five functional layers in the emerging agentic commerce stack: A2UI, AG-UI — How results are rendered to the human Visa TAP, Mastercard VI, AP2, MPP, x402 — How agents authorise and execute payments UCP, ACP — How agents discover products, build carts, and complete checkout A2A, ACP (IBM) — How agents coordinate with other agents MCP — How agents connect to external tools, APIs, and data sources The critical insight is that competition exists The most consequential competition in the stack is at Layer 3: commerce. Google's Universal Commerce Protocol and OpenAI's Agentic Commerce Protocol both aim to standardise how AI agents interact with merchants. But their architectures, philosophies, and trajectories diverge significantly. The AXD reading of this competition is that UCP and ACP are converging on different