Research interests

Calibration and decisions

How should a system act when context changes, evidence is incomplete, or confidence is unreliable? My earlier T-UEBA work informs my interest in calibration, abstention, and analyst review.

Cognitive security

Agent evaluation

Designing tasks and feedback that reveal why an agent failed: a bad tool call, a missing observation, or a flaw in the scoring rule.

Agent environments

Geometry and representation

Combining exact geometry with learned relations to reconstruct CAD while preserving editability.

Graph modeling ยท Applied epistemics

Robot planning

Comparing motion plans against geometric constraints, smoothness, reachability, and operator expectations, then testing their behavior in the complete system.

Advanced Metal Research