Coding
Designing, building, and testing complex engineering repositories.
Environments for Long Horizon Work
We design challenging worlds where AI models learn to explore and solve problems. We turn these worlds into post-training datasets and reinforcement learning environments to train the next frontier of AI.
Backed by Y Combinator and working with four top frontier AI labs, several Fortune 100 companies, and leading RL data vendors.
We focus on
Computer Use
Navigating across apps, browsers, and operating systems.
Knowledge Work
Synthesizing information and creating documents, spreadsheets, slides, and reports.
Research
Experimenting with autoresearch, machine learning, scientific workflows, and recursive self-improvement.