Realtime AI News
Shopify opens checkout to browser-based AI agents
Shopify is expanding WebMCP support to checkout, letting browser-based AI agents update order details and complete purchases once the buyer authorizes it. The change moves agents past browsing and comparison and into the final, permission-sensitive step of the shopping flow.

Shopify is expanding its WebMCP support to checkout, allowing browser-based AI agents to update order details and complete purchases with a buyer's authorization, according to TechCrunch.
The report is specific about what changes: agents no longer stop at browsing and price comparison, but can modify order information on the page and carry the payment step through to the end. Previously, this kind of automation typically halted partway and handed the final confirmation and payment back to the user.
Checkout is the most permission-sensitive stretch of any e-commerce flow. It touches addresses, payment methods, discounts and inventory at the same time, and an error in any of them maps directly to money and compliance risk. By opening that capability on the browser side, Shopify effectively moves the agent's operating surface from a backend interface onto the page the customer is already looking at.
Authorization is the hinge. As described, an agent's edits and payment actions require the buyer's authorization, which keeps the user as the decision-maker and the agent as the executor. That division of labor is a practical compromise on trust for agentic commerce today.
For merchants, the more consequential shift is where traffic and intent enter the funnel. If a growing share of purchase decisions is made by agents inside the browser, product data, inventory, promotions and the checkout experience all need to be machine-readable and machine-actionable. Optimizing for agents stops being a marketing talking point and becomes an engineering requirement.
What to watch next is how widely web-side agent interfaces like WebMCP get adopted, and how authorization and liability boundaries are drawn. Once an agent can genuinely press the pay button, who answers for a mistaken order becomes a question platforms, merchants and model providers will all have to address.
Sources
Why it matters
Checkout is where money and liability concentrate. Opening it turns agents from shopping assistants into counterparties that transact, shifting competition toward authorizable, auditable checkout rather than product recommendations.
Nearby Updates
All09/29, 02:31
Nvidia launches a platform to rein in rogue AI agents
Nvidia on Monday introduced a toolkit of software and hardware products that wraps AI agents in an independent security layer, presented by CEO Jensen Huang himself. The launch lands in the middle of a debate over whether the recent spate of rogue agents signals a step toward AGI or a conventional engineering problem in need of conventional fixes.
09/29, 02:00
Anthropic releases Claude Sonnet 5.5, calling it a cheaper, faster work partner
Anthropic has released Claude Sonnet 5.5, the newest version of its mid-range model, presenting it as a significantly cheaper and faster work partner. Media coverage puts the gain at roughly 30% faster than the previous-generation model, with fewer tokens burned.
09/29, 01:57
YouScan Upgrades Insights Copilot, an AI Agent for Social Listening
YouScan has upgraded Insights Copilot, positioning it as an AI agent for social listening. The company says the update turns social media research that used to take hours into work finished in minutes.
09/29, 01:29
Google Is Killing Off Gemini's Gems in Favor of 'Skills'
Google is shutting down Gems, the Gemini feature that let users build task-specific agents, and moving to a new approach called skills. The change comes as all-in-one AI agents such as Meta's Muse and Instinct gain ground.