Anthropic Releases AI Agent Blueprints for Shopping Agents Ahead of Holiday Season

Anthropic lays groundwork for bots that shop for you

Anthropic has blueprints for building e-commerce bots that shop on behalf of clients. That's not something many consumers want at the moment, but the AI biz this week published a set of templates for Claude-based shopping agents and merchant agents in the hope of encouraging more e-commerce businesses to implement automated purchasing. Its blueprint "contains the harnesses, patterns, and guardrails an engineering team needs to get a commerce agent running in days, with reference implementations of a shopping agent and a merchant agent for retail, travel, telecom, and ticketing platforms," the company said. Large retailers and ecommerce platforms, Anthropic observes, are using Claude to build AI agents to simplify online shopping by allowing customers to pose natural language queries to find, compare, and buy items. The buying bit may be wishful thinking: A recent Gartner survey found that while consumers use AI to find products and conduct research, they're not ready to delegate purchasing authority to AI agents. The survey found just 11 percent of consumers are willing to let AI make purchase decisions. A recent Accenture survey [PDF] is a bit more optimistic, noting, "Three in four (74 percent) consumers would let an AI agent handle routine tasks; one in three (32 percent) are ready to hand over purchase decisions; and 9 percent are open to fully autonomous shopping, before the technology is fully operational." Either way, at least AI-assisted product finding and comparison appear to be plausible activities. Anthropic's GitHub repo contains functional shopping and merchant agents that can be built with the Messages API, Agent SDK, or Claude Managed Agents. The biz's shopping agent blueprint comes with ways to connect to product catalogs, online shopping carts, checkout systems, preference databases, and purchase history databases. "A customer can say 'I need a tent, sleeping bag, and stove for a weekend trip with two kids,' and the agent can take it from there," Anthropic suggests, noting that its code supports guardrails "designed to constrain prices and products to actual catalog data, and avoids manipulative upsell patterns." Why might prices need constraint? Well, beyond the possibility of hallucinated pricing, there's considerable concern about how AI agents have the potential to compound the problems with dynamic pricing - where customers are charged different amounts for the same goods. "The rise of agentic AI, where algorithms monitor online behavior to customize costs, will likely exacerbate dynamic pricing," said the Brookings Institution earlier this year. "These agents can assess individual behavior and tailor prices based on a consumer's shopping and purchasing history." Concerns about AI surveillance pricing were discussed last month at a Senate Judiciary subcommittee hearing. In prepared remarks, Lindsay Owens, president and CEO of Groundwork Collaborative, a Washington, DC-based advocacy group, noted that already half of those using the Walmart app use "Sparky," the company's AI assistant. Those shoppers spend about 35 percent more than those who don't, Owens said. "These agents have access to swaths of data on customers - what shoppers tell them, what they've purchased in the past, and in some cases, what they've hovered over with their mouse or even what other websites they've visited," she said. "All of that can be used to infer exactly how much they're willing to pay for a product and set the price tag accordingly." Even if shoppers can be assured of getting a fair deal using AI agents, there's another concern. Monica Eaton, founder and CEO of Chargebacks911, told The Register in an emailed statement that agentic commerce looks likely to create fraud problems for merchants. There isn't yet a framework for merchants to deal with AI purchases that consumers claim they didn't authorize. "Merchants cannot become the insurer of every misunderstanding between a consumer and their AI," she said. Anthropic's templates may prove helpful for AI agent design, but the real challenge isn't technical. It's about trust - consumers have to trust that AI will act in their best interest and merchants have to trust that AI will be accountable. That may take time. ®

Anthropic launches AI agent blueprints for retailers ahead of holiday shopping season

NEW YORK, Sept 2 (Reuters) - Artificial intelligence company Anthropic is giving retailers blueprints to build shopping and merchant agents on Claude, it announced on Wednesday, as demand for internal and external conversational search tools expands ahead of the holiday shopping season. Reporting by Arriana McLymore in New York; editing by David Gaffen Our Standards: The Thomson Reuters Trust Principles., opens new tab * Suggested Topics: * Artificial Intelligence Arriana McLymore Thomson Reuters Arriana McLymore is a New York-based reporter covering e-commerce, online marketplaces, alternative revenue streams for retailers and in-store innovation. She previously reported on telecoms and the business of law.

Anthropic releases AI shopping agent blueprints for retailers

Anthropic released a blueprint Wednesday for building commerce agents on Claude, its AI model, targeting retailers, travel companies, and ticketing platforms ahead of the holiday shopping season. The package includes reference implementations of two agents: one that lives inside a retailer's app or website and helps customers search for products, compare options, and add items to their cart, and another that helps store operators with inventory, pricing, and marketing decisions. Retailers can deploy the code through the Claude API, Amazon $AMZN Bedrock, Microsoft $MSFT Foundry, or Google $GOOGL Cloud Vertex AI, the company said.

Anthropic launches AI agent blueprints for retailers ahead of holiday shopping season

AI-driven retail site visits now convert at a 60% higher rate than traffic ⁠from other sources, Adobe Analytics said last month. Artificial intelligence company Anthropic is giving retailers blueprints to build shopping and merchant agents on Claude, it announced on Wednesday, as demand for internal and external conversational search ⁠tools ⁠expands ahead of the holiday shopping season. Shoppers are increasingly using AI to compare prices, check product availability and get recommendations. AI-driven retail site visits now convert at a 60% higher rate than traffic ⁠from other sources, Adobe Analytics said last month. The blueprints are guidelines for ⁠building shopper and merchant agents for retail, travel and ticketing companies. Online agents can make preference-based suggestions and add items to shopping carts for customers. "We've seen encouraging results - cart size up about 30-35% for one partner, and customers [are] about 60% more likely to complete a purchase," said Angela Jiang, Anthropic's head of product ⁠on its Claude platform. Retailers can use the merchant blueprint to build an agent that makes suggestions on inventory, prices and marketing campaigns. It does not complete purchases on behalf of shoppers or merchants, Anthropic said.

Anthropic Built the Shopping Brain and Skipped the Wallet | PYMNTS.com

"It contains the harnesses, patterns, and guardrails an engineering team needs to get a commerce agent running in days," Anthropic said. The release ships with reference implements for retail, travel, telecom and ticketing, plus a plugin for Claude Code, the company's developer tool. Shopify and Priceline are already running customer-facing agents on Claude, and Priceline rebuilt the latest version of its assistant, Penny, on Anthropic's models. Retailers already running shopping agents on Claude have seen carts grow as much as 35% larger, with shoppers 60% more likely to complete a purchase, Anthropic said. Those are the company's own reported figures rather than an independently verified benchmark. Accenture, Mastercard and Visa are working with Anthropic to bring the blueprint to their clients and merchant networks, Digital Commerce 360 reported. Shopify has published public code repository showing how the agents connect directly to a live storefront, searching the catalog and building a cart through the merchant's own systems. Anthropic Built the Agent and Left Checkout Alone What Anthropic left out matters as much as what it shipped. The blueprint includes no payment protocol, no product catalog and no advertising layer. Those pieces stay with the retailer's own systems and payment partners, so no transaction routes through Anthropic. Shopify's implementation shows the handoff. Its agent finds products and builds a cart, then passes the shopper to the store's existing checkout, where the payment stays. Claude sits on top of a retailer's existing infrastructure as the reasoning layer, not as a new checkout competing with the merchant for the customer relationship or the payment flow. Kath Gramling, Accenture's global consumer goods, retail and travel lead, framed the moment in broader terms: "Commerce agents are quickly becoming a critical capability for organizations seeking to deliver the personalized, intelligent customer experiences that today's consumers expect," she said in comments included in Anthropic's announcement. Retailers Are Sold on Agents. Consumers Stop at the Payment. The launch lands while most retailers are still experimenting. Forty-three percent of retailers are piloting autonomous AI shopping tools, and 81% say they trust AI to operate on its own once the right guardrails are in place, according to PYMNTS Intelligence and Worldpay's "Agents of Change" report. Consumer appetite runs close behind. Some 45% of consumers say they'd be comfortable letting an AI agent complete a purchase on their behalf, rising to 54% among Gen Z specifically. That comfort thins out fast once money is actually involved. Ninety-five percent of consumers report at least one concern about agentic commerce, and only 5% say they have none, the same PYMNTS Intelligence research found. Half of U.S. consumers said they'd trust agentic commerce more if they knew fraud protections were in place. That gap between retailer appetite and lingering consumer wariness is the space Anthropic's blueprint deliberately leaves alone. It hands retailers the reasoning and discovery layer and keeps the actual transaction inside the systems and partners, Visa and Mastercard among them, that already carry the trust a payment requires. For all PYMNTS AI coverage, subscribe to the daily AI Newsletter.

Anthropic Gives Retailers Blueprint for AI Shopping Agents | PYMNTS.com

The AI company announced the blueprint Wednesday (Sept. 2). Reuters reported that the initiative comes as shoppers increasingly use AI to compare prices, check product availability and get recommendations. Adobe Analytics said last month that visits to retail sites driven by artificial intelligence were converting at a 60% higher rate than traffic from other sources, according to Reuters. Anthropic said its blueprint includes working reference implementations for both shopping and merchant agents across retail, travel, telecom and ticketing platforms. The company also is providing a Claude Code plugin and said the blueprint can be deployed through the Claude API, Amazon Bedrock, Microsoft Foundry or Google Cloud Vertex AI. The shopping agent is designed to operate inside a retailer's app or website. It can search product catalogs, assemble multiple items, use customer preferences to tailor recommendations, display comparisons and carts within a conversation and hand completed carts to checkout. It also can answer customer-service questions about orders, returns, exchanges and refund policies, Anthropic said. Payment processing remains with the retailer, which can use its existing checkout or an agentic payments provider, according to Anthropic. The shopping agent also includes controls intended to keep prices and products tied to actual catalog data and avoid manipulative upselling. The merchant agent is aimed at store operators. It can answer questions about sales performance, monitor inventory and flag potential problems, recommend pricing and promotions based on sales history and draft marketing campaigns. Anthropic said a person must approve changes before they go live. The move comes as Anthropic expands its push into enterprise AI and works to make Claude more accessible to businesses. PYMNTS reported that the company has expanded its Claude Partner Network as enterprise adoption grows, with more than 40,000 firms applying to the program and more than 10,000 consultants earning Claude certifications since its March launch. Anthropic also has been lowering the cost of running AI agents: its Claude Sonnet 5 model was introduced at an introductory price of $2 per million input tokens and $10 per million output tokens.