Designed for agents first
We work on systems designed for agents to carry out work end to end, without a person as a required step in execution.
Agent Next
Building an agentic world.
We believe the next era of work will be carried out by agents: systems that pursue goals over long horizons, coordinate with one another, and produce results that can be checked.
Mission
Agents do the work. People stay on the loop.
Large teams, in the cloud
We design for many agents working in parallel on elastic infrastructure, over tasks that run for hours or days rather than a single exchange.
People set direction
People set goals and boundaries, oversee execution, and provide feedback. We aim to make results and supporting evidence inspectable, so people can assess outcomes and intervene when needed.
Research
What we work on
Infrastructure
Agent infrastructure
Models, runtimes, and coordination that let large agent teams operate reliably.
Verification
Checking agent work
Methods for checking agent work and establishing the limits of its reliability.
Learning
Learning from experience
How agents can learn from outcomes, feedback, and failures.
Applications
Agents for science and beyond
Research on autonomous agents for scientific discovery and other real-world work.
Follow the work.
Open code and research notes as they are ready.