LoginStart beta
Ayneye
How it worksStart beta

Accuracy and confidence

Accuracy means artifact quality, evidence coverage, and honest uncertainty.

Ayneye should not be evaluated as a generic claim that CPU-first detection beats every GPU video model. It should be evaluated on whether the artifacts support the workflow, expose uncertainty, and remain inspectable.

Accuracy evaluation matrix

MetricWhat to measurePass signal
Object coverageImportant objects appear in scene_graphStable IDs and useful labels
Event coverageExpected events appear in timelineTimestamped events with evidence_refs
Evidence precisionEvidence spans support answersReviewer agrees with cited span
Uncertainty exposureLow confidence is visiblereview_required or fallback flags appear
Repeated query consistencySame question variants stay groundedAnswers cite same or improved evidence
Cost visibilityProcessing cost is visiblecost.json explains duration and mode

Where escalation may be needed

Some footage needs specialized models or human review: low-light scenes, heavy occlusion, crowded scenes, subtle gestures, cinematic semantics, identity-sensitive tasks, intent inference, and operational decisions that affect people. A credible product does not hide that. It shows confidence, flags, and escalation paths.

Recommended test set

  1. One easy clip where the target event is clear.
  2. One crowded or noisy clip.
  3. One low-light or motion-heavy clip.
  4. One representative customer clip.
  5. One ambiguous clip where review_required should appear.

Product boundaries are part of the product, not footnotes. Ayneye is not presented as a replacement for every GPU video foundation model, not a free-infinite-query engine, and not an autonomous surveillance decision system. The current beta path is controlled signup, dashboard, REST API, bounded processing, evidence artifacts, visible limits, and read-only agent/MCP-style evaluation. Hard scenes, identity-sensitive workflows, emergency response, physical access, discipline, and destructive actions require human review or remain blocked.