|

Specifications

Two specs, both Apache 2.0, both on GitHub. Telemetry defines the event model for content attribution. AIMS defines agent identity. They work independently or together.


Telemetry

v0.1 - Preview

Read on GitHub

The session-event-outcome model for content attribution in AI agent interactions. Defines how retrieval, citation, engagement, and conversion events are structured, transported, and correlated across multiple observers.

Core event types

EventWhen
content_retrievedContent fetched from source by an agent
content_citedContent referenced in an agent's response
content_engagedUser interacted with cited content
turn_started / turn_completedConversation turn lifecycle
checkout_completedPurchase confirmed - ties outcome back to content

Key concepts

  • Source roles - origin, edge, index, agent. Multiple observers can report the same retrieval from different vantage points.
  • Cross-observer correlation - the OA-Telemetry-ID HTTP header links events from different reporters into one corroborated retrieval.
  • Privacy levels - four tiers from full (complete query/response text) to minimal (only content URLs and token counts). No PII.
  • Multi-session attribution - prior_session_ids links research, comparison, and purchase sessions into a full journey.

Protocol bindings

BindingPurposeSpec
ACPEmbed attribution in Agentic Commerce Protocol checkoutsacp/rfc
UCPEmbed attribution in Universal Commerce Protocol checkoutsucp/EXTENSION

SDKs


AIMS - Agent Identity and Manifest Standard

v0.2 - Draft

Read on GitHub

Verifiable identity for AI agents that access web content. AIMS is the identity layer in the four-layer stack - it provides the verified subject that telemetry events are attributed to.

What the manifest declares

FieldWhat it declares
IdentityW3C DID (any method - did:web recommended)
LicencesContent licences held, RSL references, redistribution policies
TelemetryOpenAttribution endpoint this agent reports to
Foundation / DeploymentOptional: training data provenance, commercial context

The agent's DID in the manifest matches the agent_id in telemetry events, linking identity to usage data. Publishers resolve the DID to verify licences before granting access.

SDK

Python: pip install openattribution-aims

Machine-readable schemas

Both specs have JSON Schema definitions for validation and code generation: