Criteo has introduced its Agentic Commerce Recommendation Service, designed to power AI shopping assistants with accurate, relevant product recommendations.
“The real competitive advantage in agentic commerce will come from access to high-quality commerce data at scale,” said Michael Komasinski, chief executive officer of Criteo. “This service brings that intelligence into AI-driven shopping experiences in a way that works for the entire ecosystem, delivering relevance AI-driven shopping for consumers while respecting retailer data, brand integrity, and platform trust.”
Agentic Commerce Recommendation Service
Built on Criteo’s commerce intelligence, the Agentic Commerce Recommendation Service leverages an enterprise-grade recommendation infrastructure that can access real shopping behaviour, not just publicly available product descriptions.
Criteo’s testing has revealed that it has improved recommendation relevance by 60% compared to third-party approaches based solely on product descriptions.
The service is available through Criteo’s Model Context Protocol (MCP) and directly connects AI-powered shopping assistants with merchant inventory.
How it Works
After a customer makes a shopping recommendation request, the AI assistant queries Criteo’s Agentic Commerce Recommendation Service to identify relevant products.
Criteo then filters and ranks products based on their relevance to the customer, using real-world shopping and purchase signals. It considers factors such as product popularity, availability, and user intent.
Instead of providing raw catalogue data, Criteo returns curated product recommendations, which the AI assistant reviews. It then presents the results, compares options, and can support add-to-cart or checkout options for the customer.
