Research · AI

Agents you can hand real work to.

Our AI research asks what it takes for an agent to do useful work on someone's behalf, and to be trusted with it: grounded in facts, checked by default, and supervised where it counts.

Research areas

01

Agentic software engineering

Agents that plan, write, test and ship software, and know when to stop and ask.

02

Grounding and verification

Methods that tie every claim and every change back to evidence a person can inspect.

03

Human supervision

Approval flows, review loops and controls that keep people in charge without slowing them down.

04

Evaluation

Measuring agents on real tasks, not benchmarks, before they reach anyone's business.