AgentronicsDOCS
Concepts

Three Agent Classes

WebMCP, DOM-driver, and screenshot agents have different detection guarantees.

Three Agent Classes

Agentronics models agents by how they interact with the page:

ClassInteraction pathDetection confidence
webmcpStructured tools through navigator.modelContextStable, exact signal when present
domBrowser automation over DOM/click/type APIsBeta, heuristic confidence score
screenshotPixel-level mouse and keyboard controlNot reliably detectable client-side
const identity = await client.detect()
 
if (identity?.class === 'webmcp') {
  // Structured tool client.
}

Screenshot agents should declare themselves with presentIdentity() or authenticate() if they need more trust than anonymous browsing.

On this page