







Anthropic published an open blueprint for shopping and merchant agents. The useful distinction is between action integrity and recommendation quality: code can keep an agent’s actions authorized without proving its recommendation was fair, stable or best for the shopper.
Sep 3, 2026 at 8:07 PM
commerce-agents/docs/safety.md at fd4d59224ab96b43c6dc6888207c67b3bd5a24cf · anthropics/commerce-agents
Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included. - anthropics/commerce-agents
commerce-agents/plugins/commerce-builder/skills/commerce-evals/SKILL.md at fd4d59224ab96b43c6dc6888207c67b3bd5a24cf · anthropics/commerce-agents
Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included. - anthropics/commerce-agents
A guide to the anatomy of effective commerce agents | Claude by Anthropic
The architecture, latency & cost techniques, and eval practices for agents that make it easier to buy and sell online.

commerce-agents/merchant-agent/core/merchant_agent/gates.py at fd4d59224ab96b43c6dc6888207c67b3bd5a24cf · anthropics/commerce-agents
Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included. - anthropics/commerce-agents
commerce-agents/shopping-agent/core/shopping_agent/gates.py at fd4d59224ab96b43c6dc6888207c67b3bd5a24cf · anthropics/commerce-agents
Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included. - anthropics/commerce-agents
building commerce agents using claude · anthropics/commerce-agents@fd4d592
Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included. - building commerce agents using claude · anthropics/commerce-agents@fd4d592
Research Report 6: Agentic Shopping is Complicated and Contingent
This is the sixth in a series of short reports that help business, education, and policy leaders understand the technical details of working with AI through rig
Agentic coding and persistent returns to expertise
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Updates to Consumer Terms and Privacy Policy
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
An update on recent Claude Code quality reports
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Agent payments get rails · Sensemaker
Visa and OpenAI’s agentic-commerce partnership shows the payment layer becoming the permission layer for AI agents.
Privacy Policy
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Agents First
Every product is getting a second customer — the human who pays, and the agent who decides. A design framework for building products that AI agents can use as primary consumers.

Building Commerce Agents with Claude | Claude by Anthropic
We're launching a blueprint to help build commerce agents on Claude. It contains the harnesses, patterns, and guardrails an engineering team needs to get a commerce agent running in days.
🚨Our new research examines agentic shopping: can you consistently predict (or, using marketing, influence) what an agent chooses? Nope. We found that even small differences (viewing order of pages, memories) changed AI preferences in unpredictable ways. papers.ssrn.com/sol3/papers.cfm?abstract_id=7…