Research

Research that becomes responsible products.

We study how models, people, interfaces and enterprise systems work together under real constraints.

Agents

Enterprise agents with bounded authority

Tool use, permissions, escalation and human review.

Research area · 2026
Knowledge

Retrieval quality and evidence visibility

Permission-aware search, citations and evaluation.

Research area · 2026
Evaluation

Testing probabilistic systems

Realistic task evaluation before and after deployment.

Research area · 2026
Multimodal

Language, vision and speech

Complete workflows that combine multiple forms of information.

Research area · 2026
Human–AI

Interfaces that support judgment

Controls, sources and escalation designed around people.

Research area · 2026
Security

Secure model and tool orchestration

Least privilege, auditability and defense against misuse.

Research area · 2026