Skip to main content
The Agentic Ad Server was built from scratch for AI surfaces. Legacy ad servers were designed for web pages and video players, where ads occupy fixed rectangles or pre-roll slots. On an AI surface, the “page” is a live interaction, and intent is expressed in natural language. That requires a different architecture.

​
The request lifecycle

1

Context in

Your integration passes the conversational context for the current turn: the user’s message and your AI’s response.
2

Signals derived

The Ad Server classifies the intent into one of nine buckets (see Intent classification) and extracts structured entities: product categories, price ranges, comparison contexts.
3

Demand evaluated

Derived conversation signals and standard advertising request fields are evaluated against eligible demand. Which demand sources are eligible depends on your integration path. See Choosing your integration path.
4

Format selected

The Ad Server selects an eligible creative from the formats enabled for the AI Surface.
5

Rendered and measured

The ad renders natively in your surface. Impressions, engagements, clicks, and conversions are measured per the rules in Tracking and measurement.

​
Data handling

The current demand-partner request does not include raw conversation messages as a dedicated field. It can include derived context—such as categories, keywords, intent, sentiment, entities, brands, and language—and standard advertising fields such as IP, user agent, geography, and approved identifiers when available. Adgentek itself processes the context supplied in the serve request. Do not send raw PII or describe the integration as anonymous solely because raw messages are not forwarded in a bid field. See Privacy architecture.