
Image credit: Search Engine Journal
Google unveiled an open standard in January 2026 for artificial intelligence agents to interact directly with e-commerce websites, aiming to reshape online retail by enabling machine-first architecture.
The Universal Commerce Protocol (UCP), introduced at the National Retail Federation conference, establishes a common language for AI platforms like Google’s Gemini and Google AI Mode to engage with merchant backends.
Google developed the UCP in collaboration with major retailers and e-commerce platforms including Shopify, Etsy, Wayfair, Target and Walmart, according to a company statement.
The protocol moves beyond traditional human-centric web design, setting a new standard for how all websites will interact with AI agents, Google said.
UCP specifies a discovery endpoint at /.well-known/ucp, allowing AI agents to identify a website’s capabilities. It also includes three REST endpoints designed to streamline the checkout process.
The protocol offers transport flexibility, supporting REST, MCP and A2A communication methods, according to the official specification.
Published as an open specification at ucp.dev, the protocol allows any website, AI platform or merchant platform to implement it without Google retaining governance, the company stated.
The UCP incorporates five key properties of machine-first architecture’s Interaction pillar: discoverable actions, predictable outcomes, workflow continuity, error recovery and agent policies.
This initiative follows increasing interest in AI’s role in commerce, with companies like OpenAI and Stripe also exploring how AI can streamline transactions and user experiences.
Industry analysts, including the Baymard Institute, have frequently highlighted the need for more efficient and less friction-filled online checkout processes, a goal the UCP aims to address through automation.
Source: Search Engine Journal
Written by
Joyce de Castro
Joyce is a core team member at Rabbit Rank and the lead author covering SEO news, algorithm updates, industry trends, and actionable ranking strategies.
Keep reading
Related Articles

Cloudflare, AWS Launch Pay-Per-Crawl Systems for AI Bots
Cloudflare and AWS introduce pay-per-crawl for AI bots using HTTP 402, empowering publishers to control and mo...

Google report shows AI queries diverge from daily life activities
Google’s AI & Economy ATLAS report shows a stark contrast between what Americans ask AI about and their daily...

Agentic AI Systems Challenge EU Data Protection Regulations
Agentic AI systems, with their persistent memory and autonomous actions, are challenging fundamental GDPR prin...