Coding
Writing, debugging, and testing code across large and complex codebases.
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, Fortune 100 companies, and leading RL data vendors.
Our foci
Computer Use
Navigating across apps, browsers, and operating systems.
Knowledge Work
Analyzing company documents, spreadsheets, and business records to produce reports and recommendations.
Research
Autoresearch, machine learning, and recursive self-improvement.