Thanks to a donation from LiveRamp, IAB Tech Lab has added Agentic Audiences (formerly the User Context Protocol (UCP)) to our open-source agentic initiative.
Agentic Audiences is an open standard that defines how intelligent agents in advertising exchange signals—identity, contextual, and reinforcement information—that represent a consumer’s real-time intent and response to advertising. Unlike traditional text-based exchanges that are too slow for modern programmatic advertising, Agentic Audiences leverages embeddings: compact, learned vector representations that efficiently encode complex signals in a privacy-preserving, interoperable format.
Think of embeddings as the universal language of AI systems. Rather than exchanging thousands of raw data points or verbose text descriptions, agents can communicate through dense vectors of 256-1024 dimensions that capture semantic meaning, enable transfer learning across systems, and support the sub-100ms response times required for real-time bidding.
Agentic Audiences is now part of IAB Tech Lab’s open source agentic initiative and has been moved to our GitHub repository. We invite you to contribute and accelerate the embedding of standards into the agentic ecosystem.
Related News