Frontier RL environments, off the shelf.
The real work of verified experts, compiled into long-horizon tasks, deterministic rubrics, and resettable RL environments ready to license.
The most valuable work never made it to the internet. It lives in how a payroll specialist closes a period, how a claims adjuster reads a file, how a dispatcher talks a rate down on a live call.
Environments compound. Datasets deplete. We capture the work at its source and sell the instrument, not the delta.
Four assets from every expert engagement
One authoring flow produces a task set, a benchmark, an RLVR environment, and a correction corpus. License any cut, or the aggregate.
RL environments
Real business software, self-hosted in isolated microVM sandboxes. Every environment ships with deterministic seeds, per-episode state resets, snapshot restore, and full action telemetry, built to survive thousands of eval runs a day without polluting state.
Long-horizon task datasets
Multi-hour workflows elicited from working practitioners and confirmed by them, not written by contractors. Ground truth is a set of acceptable outcomes with tolerance bands, mandatory invariants, and disqualifying conditions.
Rubrics & verifiers
Expert-weighted rubrics compiled into code. Database assertions, numeric reconciliation, and audit-log checks grade the work. Model-graded criteria are capped, labeled, and expert-audited, never the default.
Benchmarks
Frozen, expert-baselined benchmark cuts with public leaderboards and reproducible harnesses. The human baseline is the authoring expert's own recorded cold run. Private held-out sets are available to license.
Reward integrity is the product.
A quarter of flagship agent benchmarks accept incorrect solutions. Ours grade with code: state assertions, reconciled ledgers, audit-trail checks. Model-graded criteria are capped at a fifth of any corpus, always labeled, always expert-audited.
Every verifier must reproduce the authoring expert's own recorded run before it ships.
db_assertState assertions against the environment's own database. The record either exists in the right state or it does not.
numeric_reconcileTotals, ledgers, and registers reconciled within expert-set tolerance bands. The ledger ties or the episode fails.
file_diffProduced artifacts diffed against acceptable outcome sets, not a single golden file.
audit_log_assertThe path matters. Required intermediate actions are checked in the environment's audit trail.
invariant_assertMandatory invariants that must hold at every step. Breaking one is a disqualifying condition with a terminal penalty.
From working expert to running environment
Every step hardens real expert work into something a lab can train against.
- 01
Source the practitioner
Our private expert network reaches verified specialists in occupations labs cannot staff. Identity and skill verification gate every cohort.
- 02
Elicit the work
We capture how the work actually gets done. The decisions, the exceptions, the tricks that never made it to the internet.
- 03
Author in the sandbox
The expert walks their own tasks inside a recorded environment on real software. That cold run becomes the human baseline and the ground truth.
- 04
Compile the reward
Rubric weights compile into shaped reward functions. Checkpoints become intermediate signals, disqualifiers become terminal penalties.
- 05
Verify deterministically
Every verifier must pass the authoring expert's own recorded run before it ships. If the check cannot reproduce the expert, it does not ship.
- 06
Refresh on the model clock
Agent failures reopen the task list at higher difficulty. Every frontier release gets fresh variants, harder bands, and a re-run leaderboard.
Occupations frontier labs cannot staff
Payroll administrators and claims adjusters do not work at labs and are not reachable through credential networks. We verified the whitespace occupation by occupation, then built the supply chain to reach them.
Benchmarks, published. Holdouts, licensed.
Every benchmark ships a public cut with a leaderboard and a reproducible harness. The private held-out sets never leave the registry.
Recruiter-Bench
Long-horizon, multi-stakeholder recruiting workflows: sourcing, screening, coordination, and recovery when humans behave like humans. Most agents fail the hard band.
ATS-Bench
Can agents build, fix, harden, and migrate integrations against a live applicant tracking system? 50 public tasks, 200 private, graded by webhook-verified system state.
Tell us where your model breaks. We build the environment.
Sample task packets, environment access, and benchmark holdout licensing for AI researchers, data teams, and labs. Exclusive cuts available.