Advancing how organizations understand and act.
The Ontology — a living model of an operation — can be right on Monday and wrong by Friday: sources disagree, entities merge, the world moves underneath it. That gap is where our research lives. It isn’t a lab off to the side: every initiative pushes on the platform’s core — the graph, the engines, the agents — and ships back into what you run. Open questions we’re working on, not results we’re claiming.
Where the work is pointed.
Six directions, one platform. Each asks a different question about how machines understand a changing world — and each one, when it moves, moves the whole system forward.
Knowledge Graphs
How to keep the Ontology correct as reality shifts underneath it — resolving entities, reconciling conflicting sources, and expiring stale relationships without losing history.
Spatial Computing
Reasoning about movement, geometry, and place over time, so position and trajectory become queryable facts rather than raw coordinates.
Agentic AI
Giving long-running agents reliable plans, tool use, and self-verification — so they can act on the graph and check their own work against ground truth.
Computer Vision
Turning visual streams into structured entities and events that link back to the graph, and doing it under real-world noise, occlusion, and drift.
Edge AI
Running inference close to where signals originate — trading model size, latency, and connectivity so decisions hold up when the network does not.
Reasoning Systems
Combining learned models with explicit structure, so answers can be traced, constrained, and defended — not just generated.
Grounded in the problem, shipped into the platform.
We start where the friction is real — an operational problem someone is living with — and work backward to the method. A direction earns its place only when it improves an engine, an agent, or the graph in production, so what we learn becomes part of the system people run.
- Every project starts from a real operational problem, not a benchmark.
- Work ships into the platform — engines, agents, and the graph — or it isn’t done.
- Results are held to ground truth, not to how good the demo looks.
Questions the field hasn’t settled.
The hard, unfinished parts — shared across the field, not solved by anyone. We state them plainly, because honest questions make for better work than confident answers.
Staying current
How does the Ontology stay correct when its sources disagree and the world keeps changing beneath it?
Trustworthy autonomy
How far can an agent act on its own before a human needs to intervene — and how does it know where that line is?
Intelligence at the edge
How much reasoning can move to constrained devices without losing the context that lives in the central Ontology?