Coming soon

Products

Environments, verifiers, and human data for training and evaluating models. Each line is built so correctness can be checked — or, where it cannot yet, so we can move the boundary.

RLHF

Human preference data when a checker is not enough. Pairwise judgments, ranked outputs, and reward signals from people — for the parts of the work that still need taste, context, and disagreement.

Post-training and fine-tuning data

Pre-existing datasets for post-training and fine-tuning, ready to use rather than commissioned from scratch. Demonstrations, traces, and labeled examples that bootstrap a model before RL — SFT, continued training, and the data a lab needs on day one.

Verifiable RL environments

Task worlds a model can act in, with a checker attached. Success is computed, not argued after the fact. We design the environment, the verifier, and the reliability number together.

RLSVR

Reinforcement learning for open-ended work where a structured, scalar signal can still be verified. For domains on the boundary — writing, investigation, and other tasks where pass/fail is not a single string.

Rubrics and verifiers

Scorecards that turn an output into a grade. Criteria, weights, and checkers for when the right answer is a standard of quality, not a unique token sequence.

RLVR

Reinforcement learning from verifiable rewards. Train and evaluate where a program can say yes or no: code, tools, math, and other domains with a ground-truth checker.