Preference Model

Builds RL environments and datasets for AI labs.

Produces custom data for long-horizon reasoning, software engineering and data-science tasks for frontier labs.

Supplies post-training data and RL environments for coding, multimodal and physical AI, plus off-the-shelf datasets and enterprise agent services.

Started as labeling software; now sells expert data and training environments to frontier labs, plus an agent product for engineering teams.

Software company that builds RL environments and sells them to leading AI labs.

Builds agents that design and verify custom chips, with related RL training work.