Eru learns from real work — actions, sequences, failures, corrections, and outcomes — continuously fed by PIN's live physical intelligence network.
Built to understand, guide, verify, and eventually automate physical work across human and robotic systems.
Language has models. Images have models. Code has models. Robots have control systems. But the real physical economy — tools, trades, machines, sites, risks, outcomes — remains largely invisible to AI.
Most systems see fragments. Eru is designed to model the chain: what happened, how it happened, why it mattered, and what should happen next.
Four interlocking representations. Each is useful on its own. Together they form a complete model of real physical work.
What is happening?
Workers, tools, materials, machines, gestures, hazards, environments, and task states.
Where does it fit?
Sequences, dependencies, missing steps, blocked tasks, phases, checkpoints, and constraints.
Did it work?
Inspections, rework, schedule impact, safety incidents, claims, certifications, and quality scores.
How should it be done?
Tool use, grip, contact, force, timing, body position, expert correction — embodied skill.
The moat is not footage.
The moat is verified physical work tied to outcomes.