We’re in a race between understanding AI systems and the rapid growth of their capabilities. Every breakthrough we make today improves our ability to guide them toward safe, reliable outcomes. Deploying powerful AI into high-stakes environments without insight into its decision-making isn’t just risky - it’s unacceptable.

Our mission is to provide the transparency and alignment needed to confidently deploy GenAI. We're building trustworthy AI through groundbreaking applied research and enterprise-ready tools.

Our team consists of authors of AI papers published at ICML, NeurIPS, etc. with PhD studies in mathematics, physics, and computational sciences across Carnegie Mellon University (CMU), California Institute of Technology (CalTech), and more.