5 projects
calibroute-ai
Uncertainty-aware evaluation and decision control for AI systems.
healthcare-escalation-bench
Perturbation-controlled benchmark of when healthcare LLM agents should answer, ask, abstain, or escalate.
teaching-over-solving
Teaching-over-solving diagnostic: separate how well an LLM tutor solves from how well it teaches.
memory-decision-eval
Offline scoring of agent memory decisions and observed tool calls.
shiftguard
Deterministic simulator and commit-time guards for tool-using LLM agents under infrastructure state races.