Anthropic Gives Retailers Blueprint for AI Shopping Agents
Anthropic is giving retailers a set of blueprints to build artificial intelligence agents that can help shoppers find products and assist merchants with tasks including inventory, pricing and marketing, as retailers prepare for the holiday shopping season.
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.
We’d love to be your preferred source for news.
Please add us to your preferred sources list so our news, data and interviews show up in your feed. Thanks!
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.
