The Agentic Commerce Wiki
The reference for AI agents that shop.
31 pages on how agents discover, compare and buy products: the protocols, the payments, the data and what each part of the industry should do next. Neutral, sourced and dated.
The Basics
What agentic commerce is and how an agent actually buys something.
- What Is Agentic Commerce? Agentic commerce is shopping in which AI agents discover, compare, and buy products for people. Definition, scope, players, and open questions.
- How Agentic Commerce Works The agent shopping loop step by step: intent, discovery, evaluation, checkout, payment authorization, and fulfillment, with who does what.
- Levels of Autonomy A six-level framework for how much an AI shopping agent decides and does alone, from assistive recommendations to delegated purchasing within mandates.
- Agentic Commerce Timeline A dated, sourced chronology of agentic commerce milestones from 2024 to October 2026: assistants, protocols, payment networks, and disputes.
- Glossary Plain-language definitions of agentic commerce terms: mandates, payment tokens, protocols, product data, agent identity, and more.
- Agentic Commerce FAQ Short answers to common questions about agentic commerce from consumers, brands, developers, and payments teams, with links to deeper pages.
Protocols & Standards
ACP, AP2, UCP, MCP and the rest of the alphabet soup, explained.
- Agentic Commerce Protocols: Overview A map of the open protocols behind agentic commerce: tool access, agent messaging, checkout, payment authorization and agent identity, and how they fit.
- Agentic Commerce Protocol (ACP) ACP, the open checkout protocol from OpenAI and Stripe: checkout sessions, delegated payment and Shared Payment Tokens, merchant requirements and status.
- Agent Payments Protocol (AP2) AP2, the open protocol for proving user authorization of agent payments with signed mandates; now developed at the FIDO Alliance.
- Universal Commerce Protocol (UCP) UCP, the open commerce protocol from Google, Shopify and partners: capabilities, discovery, transports, payments, governance and adoption.
- Model Context Protocol (MCP) in Commerce How the Model Context Protocol is used in agentic commerce: MCP servers for catalogs, carts and checkout, MCP Apps for shopping UI, and the protocol's limits.
- Agent2Agent Protocol (A2A) A2A, the Linux Foundation protocol for communication between independent AI agents: agent cards, tasks, bindings, governance and commerce uses.
- Visa Intelligent Commerce Visa's agentic commerce program: agent-specific tokens, spending controls, the Trusted Agent Protocol for agent identity, Intelligent Commerce Connect and partners.
- Mastercard Agent Pay Mastercard's agentic payments program: Agentic Tokens, agent registration, the Agent Pay Acceptance Framework, Verifiable Intent, trust services and partners.
- x402 x402, the open protocol that uses HTTP 402 Payment Required for per-request payments, mostly in stablecoins: how it works, agent uses and the x402 Foundation.
- Web Bot Auth Web Bot Auth: cryptographic identity for bots and AI agents using HTTP Message Signatures, its IETF status, signed agents, and how merchants use it.
Ecosystem
The agents, data, payments and platforms that make it work.
- Shopping Agents and AI Surfaces Where AI shopping happens: ChatGPT, Google AI Mode and Gemini, Perplexity, Copilot, Alexa for Shopping, Meta Muse, Claude, and retailer agents.
- Product Data for AI Agents Why structured product data underpins agentic commerce, how it differs from SEO, AEO and GEO, and what good data, feeds and catalog APIs look like.
- Product Search vs. Web Search How product search APIs and web search APIs for AI agents differ, what each returns for a shopping query, and how developers combine them.
- Payments and Trust in Agentic Commerce How agents pay without holding card numbers: tokenization, delegated payments, mandates, SCA and 3DS, network agentic tokens, wallets, and disputes.
- Commerce Platforms and Agent Channels How Shopify, Salesforce, commercetools, BigCommerce, Adobe Commerce, Wix and marketplaces connect merchants to AI shopping agents.
- Agentic Commerce Market Landscape A map of agentic commerce company categories with named examples, plus published market forecasts from McKinsey, Morgan Stanley, Bain, Gartner and Adobe.
Key Topics
Identity, fraud, attribution, liability and getting found by agents.
- Agent Identity and Fraud Know Your Agent, telling good agents from bad bots, cryptographic agent signatures, agentic fraud vectors such as prompt injection, and practical mitigations.
- Attribution and Affiliate in Agentic Commerce Why click-and-cookie attribution breaks when AI agents shop, how referrals are tracked today, commission models in agent surfaces, and how to measure.
- Consumer Protection and Liability Who bears the loss when an AI agent buys the wrong thing: disputes, chargebacks, and the regulatory picture in the US and EU. An overview, not legal advice.
- Agent Optimization (GEO for Commerce) How to make products discoverable and recommendable by AI shopping agents: data completeness, feeds, reviews, crawlability, llms.txt, policies, and testing.
Playbooks
What to do about it, by role.
- Playbook for Brands and Merchants A practical guide for DTC and wholesale brands preparing for AI shopping agents: product data, agent surfaces, protocols, pricing, and returns.
- Playbook for Developers How to build shopping agents and merchant integrations: agent architecture, product search options, MCP, ACP and UCP checkout, payment tokens, evals, and security.
- Playbook for Enterprises and Large Retailers How large retailers and enterprises approach agentic commerce: build vs. partner, owned agents, operating model, governance, and B2B agentic buying.
- Playbook for Affiliates, Publishers, and Agencies How agentic commerce reshapes affiliate networks, publishers, and performance and SEO agencies: funnel shifts, new services, attribution, and commission models.
- Playbook for Payments Providers What agentic commerce means for PSPs, acquirers, issuers, wallets, and BNPL: agentic tokens, mandates, risk models, network programs, and disputes.
No pages match. Try the glossary, or ask the 8 Ball.