🔍 Read the full analysis: Why Walmart Lets AI Shopping Agents In While Amazon Blocks Them on ThorstenMeyerAI.com
Get the latest gadgets delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
TL;DR
Walmart announced an Agent Gateway and shopper-controlled Agent Profiles on Oct. 21, opening a structured route for approved AI agents to browse and buy. Amazon has blocked Meta’s Muse agent, citing its terms and concerns about how it operates. The contrast reflects a developing contest over access, customer relationships and how purchases are attributed.
Walmart is opening a managed route for AI shopping agents, while Amazon has blocked Meta’s Muse, setting up a dispute over how automated assistants access stores and who controls the purchase. Walmart announced its Agent Gateway and Agent Profiles on Oct. 21; Amazon says Muse’s access violated its Conditions of Use.
Walmart’s Agent Gateway is designed to let approved agents search inventory and make purchases through a structured connection rather than browse the retailer’s consumer website as a person would. The company also announced Agent Profiles, which can give shoppers controls such as spending limits. The source report describes the gateway as using the Model Context Protocol, or MCP.
Amazon took the opposite approach with Muse. After Meta launched the agent on Sept. 8, Amazon blocked it on Sept. 20. Amazon said Meta had not informed it that Muse would shop on its site, that the agent did not identify itself, and that it appeared to capture and store customer credentials. Meta’s launch post said Muse “has no visibility into people’s passwords or payment methods.” Those statements are competing accounts; the source material does not independently establish how Muse handled credentials.
Meta said on its Oct. 21 earnings call that more than 10 million people in the US and Canada had set up Muse in roughly six weeks, and that shopping was its most common use. Meta also reported an average purchase above $200. These are company-reported figures; the material does not provide independent verification or a detailed method for calculating them.
Agentic shopping
Three ways an AI agent buys for you
Every fight between shops and AI agents comes down to which of these three routes the agent uses, and whether the shop agreed to it.
The browser, like a human
The agent opens pages built for people, signs in with your login and clicks through checkout. Works almost anywhere, which is why shops object: they can't tell the agent from you.
Examples: Meta's Muse (from a virtual machine in Meta's cloud), Perplexity's Comet (from your own computer)
The shop's own agent door
Approved agents search and buy through a structured interface instead of clicking through pages. The shop sets the rules.
Examples: Walmart Agent Gateway (MCP, beta), Shopify MCP server and WebMCP checkout tools
Shared protocols
Common rules for who the agent is, what you allowed, and how the checkout and payment are confirmed.
Examples: Personal Agent Protocol (draft), Universal Commerce Protocol, Agentic Commerce Protocol
The protocols competing to be the standard
| Protocol | Backers | Covers | Status |
|---|---|---|---|
| Personal Agent Protocol (Poppy) | Sierra, Meta, Walmart, Shopify, Stripe + 35 design partners | Agent identity, customer permission, one session across site, API and company agent | Draft 0.1 (9 Oct 2026) |
| Universal Commerce Protocol (UCP) | Google, Shopify; site also lists Etsy, Wayfair, Target, Walmart, Amazon, Microsoft | Discovery, cart, checkout, orders; payment mandates via AP2 | Published |
| Agentic Commerce Protocol (ACP) | OpenAI, Stripe | Checkout between agent and merchant | Open source; ChatGPT's own checkout scaled back in March 2026 |
What a careful agent purchase looks like
- You give the task and a limit, for example a $50 cap.
- The agent identifies itself to the shop and gets only the access you approved.
- It prepares the cart and shows you an approval card.
- Payment goes through a token or one-time card, so the agent never sees your card.
- The shop’s normal returns apply if the agent got it wrong.
Sources: Meta (8 Sep 2026), Walmart (21 Oct 2026), TechCrunch on Shopify (28 Sep 2026), Sierra (9 Oct 2026), ucp.dev, agenticcommerce.dev, OpenAI (24 Mar 2026). Purchase steps: Walmart’s agent terms and Meta’s Muse description.
Powered by Thorsten Meyer AI
Who Controls the Agent-Made Sale
The split could affect which products shoppers can compare, which retailers an agent can reach and where a transaction takes place. An agent using ordinary browser pages may reach stores that have no dedicated connection, but retailers may have less visibility into whether a visitor is a person or automated software. A retailer-approved gateway gives the store more control over access and may make inventory and checkout information easier for agents to use.
There is also a commercial stake in owning the customer relationship and purchase path. The source report says Meta expects to earn a small fee from transactions, while retailers may want shoppers to use their own sites, apps or assistants. Publishers and affiliate businesses could also be affected if an agent reads product reviews and completes a purchase without clicking a tracked referral link. The extent of that impact is not established in the material.
For shoppers, convenience brings practical questions about spending authority, payment security and returns. A retailer’s agent policy can determine whether an assistant can compare prices there at all; an agent’s own controls determine what it is permitted to buy. Shoppers may need to check whose checkout and return terms apply before delegating a purchase.
Popular right now
TCL 85 Designer Series QD-Mini LED TV (Model 85A400U) with Google Smart TV
Ninja Foodi DZ201 8-Quart DualZone 6-in-1 Air Fryer
Dyson Cyclone V10 Origin Cordless Vacuum
As an affiliate, we earn on qualifying purchases.
From Browser Bots to Retail Gateways
The disagreement reflects three approaches to agent shopping. A browser-based agent, such as Muse as described in the source, interacts with pages designed for people. That can work across many websites, but retailers may object that the automated visitor is difficult to distinguish from a customer. A second approach is a retailer-approved connection: Walmart’s gateway and tools such as Shopify’s structured checkout are intended to provide agents with defined ways to access commerce services.
A third approach is a shared protocol intended to standardize how agents and merchants communicate. The source identifies the Personal Agent Protocol, backed by Meta, Sierra and other partners, as a draft published in October 2026. It also describes Google and Shopify’s Universal Commerce Protocol and OpenAI and Stripe’s Agentic Commerce Protocol. Their aims and adoption differ, and the existence of a protocol does not mean all retailers accept every agent.
The rollout has already shown limits. According to the source, OpenAI launched Instant Checkout in ChatGPT using its protocol in September 2025, then changed direction in March 2026, saying the initial version lacked the flexibility it wanted and that it would let merchants use their own checkout experiences while it focused on product discovery. The source also reports that Meta announced retail connectors in September for Walmart and other brands, but access remains dependent on each retailer’s policies.
Access, Safety and Adoption Remain Open
The source does not establish how widely Walmart’s gateway will be adopted, which agents will receive access, or whether the announced controls will work consistently across shopping tasks. It also does not provide independent testing of Muse’s credential handling or resolve the conflicting claims from Amazon and Meta.
It remains unclear how competing commerce protocols will interoperate, how retailers will attribute sales generated by agents, and whether shoppers will have a consistent way to dispute an unauthorized purchase. The reported figures for Muse are Meta’s own, and the material does not give independent measurements of how often agents successfully complete purchases. HUMAN Security data cited in the source says 81% of agent requests in its September dataset went to product and search pages and 2.4% to checkout and payment; the report does not provide a fuller comparison baseline, so those figures describe that dataset rather than all agent shopping.
Retailer Access Rules Take Shape
The immediate test is whether Walmart’s gateway moves from an announcement into broad, usable access for approved agents, and what retailers require before granting that access. The next developments to watch are which agents connect, what shopper permissions they must honor, and how checkout and returns are handled.
Amazon’s position on Muse and outside agents may also change, but the source reports no announced reversal or timetable. As protocols develop and retailers decide whether to accept them, shoppers should check agent spending permissions, payment safeguards and the seller’s return policy before allowing an assistant to place orders.
Key Questions
What did Walmart announce?
On Oct. 21, Walmart announced an Agent Gateway for approved agents to search inventory and shop through a structured connection, along with Agent Profiles that can give shoppers controls such as spending limits.
Why did Amazon block Meta’s Muse?
Amazon said Muse was an unauthorized agent, had not identified itself, and appeared to capture and store customer credentials. Meta said Muse had no visibility into users’ passwords or payment methods; the source material does not independently resolve the dispute.
Can an AI agent shop at every retailer?
No. Access depends on each retailer’s policies. Some agents use ordinary browser pages, while other retailers offer dedicated connections for approved agents. Amazon’s block on Muse is one example of a store restricting access.
How common is AI-agent checkout so far?
The source cites HUMAN Security data saying that in its September dataset, 2.4% of agent requests went to checkout and payment pages, while 81% went to product and search pages. Those figures describe the cited dataset and do not establish a rate for all shopping agents.
What should shoppers check before delegating a purchase?
Check the agent’s spending limit, purchase-approval settings and payment method, and confirm which retailer’s return policy applies. The source material does not establish that every agent or retailer offers the same safeguards.
Source: ThorstenMeyerAI.com
