Learn

← Track I: IAB Tech Lab Agentic (AAMP)
L4-L5

I3

Agentic Audiences: signals at machine speed

In this lesson you will
  • Explain Agentic Audiences (formerly the User Context Protocol, contributed by LiveRamp): exchanging audience signals between agents as vector embeddings rather than text.
  • Explain why embeddings allow fast, privacy-aware matching at machine speed.
  • Connect this to Track D identity and the AdCP Signals module: different routes to the same goal of relevance.

Audiences have always moved as lists and segment IDs: text that has to be matched, synced, and reconciled between systems. That is slow and leaks information. Agentic Audiences proposes a different representation, built for machine speed.

Agentic Audiences (formerly the User Context Protocol, contributed to the IAB Tech Lab by LiveRamp) exchanges audience signals between agents as vector embeddings rather than text. An embedding is a compact numeric representation of meaning. Comparing embeddings is fast and does not require passing around the raw segments, which makes matching quicker and more privacy-aware.

Key idea

The goal is the same one from Track D: get the right audience in front of the buyer so relevance, and price, go up. The difference is the mechanism. Instead of syncing segment lists, agents compare embeddings at machine speed.

It sits alongside the AdCP Signals module from Track H. Both are about activating audiences for agents; Agentic Audiences is the IAB Tech Lab’s fast, embedding-based route. Consent and privacy rules still apply, the representation just makes the exchange leaner.

Quick check

What is the main difference between Agentic Audiences and passing traditional segment lists, and what stays the same?

Key concepts
Agentic Audiences (formerly User Context Protocol)Vector embeddings vs text-based signalsMachine-speed, privacy-aware matchingRelation to identity and AdCP Signals
Going deeper

To really lock this in: explain in plain terms why moving audience signals as embeddings can be faster and more privacy-aware than passing raw segments, and how it connects to match rate.

Where this leads
LEARN

Connects Track D identity (D4) with the AdCP Signals Activation module (H4).

Bidcliq Academy · I3: Agentic Audiences: signals at machine speed