Definition & Guide

What Is Agentic Commerce?

Agentic commerce is shopping powered by AI agents that autonomously search, compare, negotiate, and purchase on your behalf—fundamentally transforming how commerce works.

What it is: AI agents that act on your behalf—not just answering questions, but completing multi-step shopping tasks from discovery to checkout.
What it changes: Commerce shifts from humans browsing websites to agents reasoning through constraints, preferences, and tradeoffs.
Why it matters: McKinsey projects a $3-5 trillion global market by 2030. This isn't incremental—it's a fundamental rewiring of how buying and selling works.

How Agentic Commerce Works

Unlike traditional shopping, where you browse, click, and compare manually, agentic commerce delegates these tasks to an AI that can reason through your requirements.

You Express Intent

"Find a birthday gift for my mom under $75—her birthday is March 15th, she likes gardening, and she hates anything too techy."

Agent Understands Context

The agent parses the recipient (mom), occasion (birthday), date (March 15th), budget ($75), interests (gardening), and avoidances (tech), then builds a constraint profile.

Retrieves & Filters Options

It queries product catalogs, filters by category (gardening, home), excludes electronics, applies the $75 budget cap, and ranks options by fit.

Evaluates & Decides

It weighs products against your constraints—price, reviews, availability, shipping speed—and selects the best match.

Executes Transaction

It completes the purchase using authorized payment methods, within spending limits you've set.

Explains Reasoning

"We chose a ceramic planter set ($68) with high ratings from gardening enthusiasts. It's gift-wrapped and arrives two days before her birthday."

Three Ways Agents Interact

McKinsey identifies three interaction models emerging in agentic commerce:

Agent-to-Site

Your personal agent talks directly to a merchant's website or API. It browses, compares, and purchases just like you would—but faster and with perfect recall of your preferences.

Agent-to-Agent

Your agent negotiates with a retailer's agent. They can haggle on price, arrange bundle discounts, or coordinate complex transactions that would take humans hours.

Brokered Agent-to-Site

Intermediary platforms coordinate multiple agents across multiple merchants—orchestrating complex purchases like travel itineraries or home renovation projects.

Agentic Commerce vs.
Traditional Shopping

This isn't just "better chatbots." Agentic commerce represents a fundamental shift in who—or what—does the shopping.

Traditional E-commerce Conversational Commerce Agentic Commerce
Who acts Human browses & clicks Human chats, AI assists AI agent acts autonomously
Discovery Search bars, filters, ads Chat-based Q&A Agent reasons through data
Decision Human compares options Human decides with AI help Agent decides within parameters
Execution Human checks out Human approves purchase Agent completes transaction
Speed Minutes to hours Minutes Seconds to milliseconds
Complexity Limited by human patience Limited by conversation Handles dozens of constraints

The Key Difference

Conversational commerce helps you shop—agentic commerce shops for you. The agent doesn't just answer questions—it takes action, makes decisions within your boundaries, and completes transactions. You set the constraints; the agent handles the rest.

Agentic Commerce in Action

These aren't hypotheticals—they're the kinds of complex, constraint-heavy shopping tasks that agents handle today.

Example 1: Skincare with Complex Constraints

"Recommend a retinol serum for acne scars that's safe for sensitive skin and good for someone just starting retinol."

What the agent does:

  • Understands the goal (fade post-acne marks with retinol)
  • Recognizes "safe for sensitive skin" → filters to gentle, fragrance-free formulations
  • Knows "just starting retinol" → prioritizes low-concentration options with clear usage guidance
  • Checks ingredient conflicts → avoids products with stacked exfoliants that could cause irritation
  • Returns a recommendation with an explanation

"We chose a low-strength retinol because you mentioned sensitive skin. Start 2-3x per week and alternate nights with other actives. This product has strong reviews from users with similar skin concerns."

Why regular search struggles: Typing "retinol for acne scars sensitive skin" into a search box returns thousands of results with no reasoning about why one product is safer than another for someone just starting out.

Example 2: Urgent Skincare, Lots of Constraints

"Can you put together a pregnancy-safe, fragrance-free dark-spot routine under $60 that gets here by Friday?"

What the agent does:

  • Keeps it pregnancy-safe → avoids ingredients not recommended during pregnancy
  • Chooses safer options for dark spots (vitamin C, niacinamide, azelaic acid)
  • Makes sure it arrives by Friday → filters for fast shipping
  • Stays under $60 total
  • Only picks fragrance-free products
  • Builds a full routine (cleanser + treatment + sunscreen), not a random list

"Because you're pregnant, we skipped ingredients that aren't recommended and chose gentler options for dark spots instead. Everything is fragrance-free, arrives by Friday, and the full routine comes to $54."

Why regular search struggles: A normal search makes you do the work—you'd have to check pregnancy safety, fragrance-free labels, shipping speed, and price for each product, then figure out what routine actually makes sense. An agent applies all those filters at once and gives you a coherent plan.

Smart Reordering

"Reorder my usual moisturizer, but if the price increased more than 10%, find me an alternative."

The agent checks the current price against your last purchase, finds comparable products if needed, and explains the tradeoff.

Cross-Platform Comparison

"Find the best deal on this sunscreen across Amazon, Sephora, and Ulta—apply any coupons."

The agent queries all three retailers, applies available promo codes, factors in shipping, and returns the best total price with reasoning.

Autonomous Substitution

"Order my usual cleanser—if it's out of stock, find the closest match."

The agent checks inventory and, if it's unavailable, finds products with matching attributes (same skin type fit, similar ingredients, comparable reviews) and explains why.

Who's Building
Agentic Commerce Right Now?

This isn't a future concept—major technology companies and focused innovators are deploying live products and protocols today.

OpenAI + Stripe

Agentic Commerce Protocol (ACP) — Powers ChatGPT Instant Checkout. Users can complete purchases directly in chat without leaving the conversation.

Google

Agent Payments Protocol (AP2) — Open protocol backed by Mastercard, PayPal, and Amex. Uses cryptographic mandates for verifiable, auditable transactions.

Catena Labs

Agent Commerce Kit (ACK) — Open-source toolkit addressing why legacy payment rails fail for agents: they're too slow, too expensive for micropayments, and require human authorization. ACK provides wallets, verified identity (ACK-ID), and spending rules (ACK-Pay)—the financial primitives agents actually need.

Anthropic

Model Context Protocol (MCP) — Standard for AI to connect with external tools and data sources. The "USB for AI integrations."

Perplexity

Buy with Pro — In-chat shopping experience integrated with PayPal and Venmo. Search leads directly to purchase without leaving the interface.

Visa & Mastercard

AI-ready cards and Agent Pay — Payment networks building infrastructure for agent transactions, including tokenized credentials and programmable spending limits.

While tech giants build end-to-end platforms, open-source initiatives like Catena Labs' ACK provide the foundational building blocks—identity, wallets, transaction rules—that let any developer build agentic commerce capabilities.

The Protocols Powering
Agentic Commerce

For agents to transact across platforms, they need shared standards—much like HTTP enabled the web. Five key protocols are emerging.

ACK (Agent Commerce Kit)

Catena Labs — Open-source financial primitives for agents: verified identity (ACK-ID), wallets, and programmable spending rules (ACK-Pay). The base layer that lets agents hold funds and transact.

ACP (Agentic Commerce Protocol)

OpenAI + Stripe — Enables agents to discover merchant capabilities, browse products, build carts, and complete checkout. Powers ChatGPT's instant purchasing.

AP2 (Agent Payments Protocol)

Google — Payment-agnostic protocol using cryptographically signed mandates. Creates auditable trails linking user intent to agent actions. Backed by major payment networks.

MCP (Model Context Protocol)

Anthropic — Universal standard for AI to access external resources, tools, and data. Enables agents to connect with any system that implements the protocol.

A2A (Agent-to-Agent)

Open Standard — Allows agents from different platforms to discover each other, exchange capabilities, and coordinate actions. The foundation for agent negotiation and collaboration.

These protocols are still evolving, and the industry hasn't consolidated around a single standard. But the direction is clear: agents need interoperable ways to discover, transact, and verify—and the infrastructure is being built now.

What Merchants Need
to Be Ready

When your next customer is an AI agent, your infrastructure needs to change. McKinsey identifies six key domains.

Product Data Quality

Agents need structured, semantic data they can reason about—not marketing copy. Ingredients, specifications, use cases, and compatibility signals must be machine-readable.

Real-Time Inventory & Pricing

Stale data breaks agent trust. If an agent recommends something that's out of stock, users lose confidence. Real-time accuracy is table stakes.

API Infrastructure

Agents need programmatic access, not human-facing websites. Product discovery, cart management, and checkout must be API-accessible.

Identity & Authorization

How do you verify an agent is authorized to buy? New frameworks like "Know Your Agent" (KYA) are emerging alongside traditional KYC.

Fulfillment Signals

Agents need to know delivery times, shipping costs, and return policies to make informed decisions. These must be exposed programmatically.

Loyalty & Personalization

If your loyalty program isn't API-accessible, agents can't apply benefits. Personalization data needs to flow to agent systems.

Risks and Open Questions

Agentic commerce isn't without challenges. Honest acknowledgment of risks builds trust—and the industry is actively addressing them.

Authorization & Consent

Who's responsible when an agent exceeds its intended scope? Protocols like AP2 address this with cryptographic mandates and spending limits, but frameworks are still maturing.

Errors & Guardrails

Agents can make mistakes or misinterpret intent. Robust fail-safes, human-in-the-loop review for high-value transactions, and clear rollback mechanisms are essential.

Trust Varies by Market

Some regions are more cautious about automated payments. In Germany and Japan, many consumers prefer traditional payment methods. Adoption will be uneven.

Accountability Gaps

When an agent-driven purchase goes wrong, who's liable? The AI platform? The merchant? The user? Legal frameworks are still catching up to the technology.

These are solvable problems. The industry is addressing them through spending limits, audit trails, human approval for significant purchases, and evolving regulatory frameworks. The direction is toward more trust, not less.

The Scale of What's Coming

$3-5T
Global Market by 2030
$1T
US B2C Retail Alone
44%
Prefer AI Search Over Traditional
800M
Weekly ChatGPT Users

"This is not a wait-and-see moment. Before long, nearly all retailers will have to grapple with the fact that a significant percentage of their customers will not be human users, but rather, AI agents."

— Lareina Yee, McKinsey Senior Partner

McKinsey notes this transformation can move faster than prior e-commerce revolutions because agents can "ride on the rails" of existing digital infrastructure. The 5.6 billion people already connected to the internet don't need new hardware—just new software.

Getting Started with
Agentic Commerce

Whether you're a merchant preparing for agent traffic or exploring how to build agentic experiences, the transformation is underway.

For Merchants

Learn how to make your catalog agent-ready. Understand the infrastructure requirements and see how leading platforms are preparing for agent traffic.

Explore the Platform

For Early Adopters

Join organizations building for the agentic commerce era. Get early access to infrastructure that enables agent-ready experiences.

Request Early Access

Want to dive deeper? Explore our Resource Hub for protocol documentation, analyst reports, and the latest developments.

Go Deeper: The Agentic Commerce Manifesto

Why vector search isn't enough—and what comes next. Our thesis on decision geometry and the NoVEC moment.

Read the Manifesto

Frequently Asked Questions

What is agentic commerce?

Agentic commerce is AI-powered shopping where intelligent agents autonomously search, compare, negotiate, and purchase products on your behalf. Unlike chatbots that just answer questions, agents take action—completing multi-step transactions within parameters you set.

How is it different from conversational commerce?

Conversational commerce uses AI to assist humans who still make decisions and complete purchases. Agentic commerce goes further: the AI agent makes decisions and executes transactions autonomously within your boundaries.

Do AI agents actually spend money?

Yes. With protocols like ACP and AP2, agents can complete real purchases using cryptographic verification and spending limits to ensure they only act within authorized boundaries.

What data do merchants need?

Structured product data that agents can reason about—real-time inventory, clear pricing, ingredient/specification details, shipping options, and return policies. The more semantic and machine-readable, the better.

How does authorization work?

Emerging protocols use cryptographically signed mandates linking user intent to agent actions. Users set spending limits, approve merchant categories, and define constraints. Every transaction creates an auditable trail.

What's the biggest risk?

Authorization errors (agent exceeds scope), cascading failures, and accountability gaps. The industry is addressing these through spending limits, human-in-the-loop approvals, and detailed audit trails.

When will this become mainstream?

It's already beginning. ChatGPT Instant Checkout, Perplexity Buy with Pro, and Google's AP2 are live. McKinsey projects $3-5 trillion globally by 2030, with 44% of AI search users already preferring it.

How can my business prepare?

Three priorities: (1) Structure product data for machine readability, (2) Ensure real-time accuracy for inventory and pricing, (3) Expose key information via APIs—agents need programmatic access.