LoginStart beta
Ayneye
QuickstartStart beta

Artifact

scene_graph.json turns footage into queryable World-State.

The scene graph stores detected objects, zones, relationships, events, confidence, and evidence references for applications and agents.

Example shape

{
  "objects": [{"id":"obj_1","label":"vehicle","confidence":0.82}],
  "events": [{"type":"entered_zone","subject":"obj_1","evidence_refs":["ev_001"]}]
}

How to use it

Store scene_graph.json by execution_id and artifact_version. Use it for dashboards, timeline filters, event lists, and read-only agent memory.

Review posture

Do not treat an artifact field as a final decision. Pair important artifact claims with evidence references, confidence, detector warnings, and human review boundaries when the workflow is high-risk.

A good product surface links the artifact to the user interface. When a reviewer clicks an event, the UI should show the timestamp, supporting evidence, confidence, and any detector warning. When an answer is generated, the same evidence should be visible. This makes debugging possible and prevents the documentation from becoming a theoretical schema list that developers cannot operationalize.