Expert-built RL environments beyond software engineering
The work professionals are paid for, rebuilt as environments an agent can learn from. Each ships with a reference solution and a verifier stress-tested against reward hacking.
Our team
Domains
The agent works in the tools of the trade and delivers the files a professional would.
Electronics
Architecture
Motion design
3D animation
Games
Biology
Custom
We draw on our network of experts to build tasks in your domain.
Built by domain experts
-
The expert does the work
A working professional solves the task in their own tools. That is the reference solution.
-
We build the task
The brief, the environment and the verifier, in Harbor format.
-
We probe and attack the verifier
Known good and bad work first, then attacks.
-
QA
Only a task that passes ships.
Formats
Tasks ship in the Harbor format, so they run in the harness you may already use.
- Harbor format
- Every probe, attack and model trial included
Licensing
Where a task uses a firm's real files, they are licensed, with signed consent on file.
A reward you can train against
A verifier that can be gamed teaches a model to game it. We attack ours before it ships and close what the attacks find.
Every task passes three layers of QA
- 01
Automated probes
The reference scores full reward on every run. A no-op scores zero. Breaking one requirement loses reward.
- 02
Attacks
Agents try to get reward without doing the work. We close every hole before the task ships.
- 03
Expert review
The expert confirms the scores on model trials match their own judgment.
Scores are computed by code from the delivered files, in an isolated container with no network.
The right difficulty for your model to learn from
Too easy teaches nothing. Too hard gives no signal. We run your model on every task and ship the ones in your target band.
Rig a character in Blender and animate a kick from reference video
Environments built for your lab
Custom environments to your spec. We start with a pilot.
Scope
Domains, tools, target model
Sample
Nine tasks to judge quality
Pilot
A small batch in your domains
Calibrate
Runs against your model
Deliver
Harbor, with every trial
↺ After the pilot: scale, checked against your evals
> request --samples
Nine runnable tasks with reference solutions, verifiers and every trial.