SENTINEL | Igor Eduardo

The public SENTINEL work is an on-device computer vision system, trained locally on Apple Silicon with MLX and YOLO26. This note restates only what is already on the site and in the public demo.

The homepage milestones record the result as Winner · webAI Build Challenge — Enterprise Track · 2026. The system is described there as built for offline casualty triage — locally trained models, zero cloud dependency, designed for environments where connectivity cannot be assumed.

Problem: Offline casualty triage
Constraint: Connectivity cannot be assumed
Decision: Local MLX + YOLO26 on Apple Silicon
Evidence: Public demo

What is public

The homepage names SENTINEL as on-device computer vision, trained locally on Apple Silicon with MLX and YOLO26. The same copy states the operating constraint in one clause: locally trained models, zero cloud dependency, designed for environments where connectivity cannot be assumed.

A public demo is linked from that milestone: youtu.be/c2v5Mdg5fpw. This note does not add metrics, authorship claims, or other statements beyond those public sources.