Where models learn to act
We build RL environments, evals and benchmarks out of real enterprise workflows. The people who do that work for a living grade the runs.
Three instruments, one question: can it do the job
The agent practises the task in a working copy of your software, failing and improving well before production.
A practitioner grades that same work against criteria drawn from how your field judges it.
A standard test built from tasks nobody published, so a model cannot memorise its way to a score.
A model that can do the job.
Where public scores stop being useful
A score only means something once you know what got tested and who graded it. Here are three of ours, next to the public suites the same models sit on.
LH2-SWE-REPO
The model fixes failing tests, reviews PRs and closes incidents inside a licensed enterprise monorepo, under live CI, with the original issue thread for context.
LH2-OPS-AGENT
The agent carries a workflow across CRM, ticketing and docs: six connected applications, with the escalations and hand-offs an ops team runs.
LH2-CLIN-REASON
Longitudinal patient cases built from de-identified records. Work the chart, order the tests, commit to a diagnosis, write it up.
Environments built from real work
Six domains, each a working simulation of a job someone does for a living. A model can practise, fail safely, and improve before it touches production.
Software engineering
A live codebase: broken tests, open PRs, failing CI. Can it fix things the way a senior engineer would?
Agentic SaaS operations
CRM, helpdesk and docs, which is an ops analyst's morning. Fill the forms, route the tickets, escalate the right ones.
Clinical reasoning
A de-identified patient file. Decide what is wrong, order the right tests, write it up. Physicians grade it.
Finance & legal ops
Real filings and contracts. Reconcile the numbers, redline the clauses, file. CAs and counsel grade it.
Embodied, from factory-floor capture
A robot in a simulation built from real production footage. Grasp, place, move, and stay inside the safety envelope.
Red-team arenas
Security practitioners try to break the agent. It is scored on whether it spots the attack and holds its guardrails.
How the training signal gets built
Capture the workflow
We instrument the real task, whether that is a repo, a chart or a workflow, from a licensed source.
Define the action space
We model the tools, states and transitions the job allows.
Write the reward
Domain experts write the rubrics and grade the trajectories, which makes the reward hard to game.
Calibrate & version
We run inter-rater checks, hold out splits, and version each release.
Run it your way
An environment has to sit where the work already lives. However closely you hold your data, one of these three lets your models train against it without moving it.
LH2-hosted
We run the environments and you hit an API. It is the quickest route from contract to first episode, and the task manifest, grader rubrics and per-episode traces all come through the same endpoint.
Inside your perimeter
We ship containerised environments into your own infrastructure. You keep the network boundary, the logs and the weights. We send the environment, the rubrics and the version history.
Built with your team
A joint programme on shared IP terms. Your practitioners write the reward alongside our calibration process, and you decide whether to publish the benchmark or keep it.
Benchmark against reality
Run your model through one environment and look at the gap.
Request an eval run