Index
Research
The open problems between real work and models that can do it. Publications will follow.
- A-01Tasks
Long-horizon knowledge work
Hard tasks drawn from inside companies: many documents, many tools, goals that take an agent days or weeks to reach rather than minutes.
- A-02Environments
Environments from live work
Offline snapshots of the environment around real agent traces, including what the user intended and what they did after the output.
- A-03Verifiers
Grading open-ended work
Knowledge work has many good answers and many bad paths to them. Rubrics and evals informed by real outcomes, not guesses.
- A-04Integrity
Reward hacking
Models find cheats in inconsistent environments and notice when they are in a simulation. We build environments that hold together, and tooling that catches the hacks.
- A-05Structure
Organisations as timelines
The full history of human and agent decisions as a code-backed ontology with timeline states, so real structure can seed tasks at scale.