ActionBench: discovering hidden failure modes of agents
Evaluating how agents decide, use tools, and cross boundaries.
Research
The systems, methods, and experiments that shape how we build and safeguard AI products.
Read
PolicyGuard: evaluating runtime control for AI actions
Measuring the real-world performance of action-level guardrails.
Preprint · Security
Coming soon
Tool authorization failure modes
Where permissioning breaks down when models try to act.
Infrastructure
Coming soon
Policy enforcement under pressure
Keeping control decisions fast when agents run at production scale.
Training
Coming soon
Designing human approval loops
Making reinforcement from review practical for production agents.