Our mission
The intelligence frontier keeps advancing every day. But are your agents delivering better outcomes on what matters?
For enterprises, the promise of agents is more work completed reliably, with less human intervention and a lower cost per successful task. As we reach abundance of intelligence for most economical tasks, the bottleneck to AI adoption is reliability. Whether agents work on your data, your use case and your edge cases.
Today, we’re launching NeoSigma and our mission to empower every organization to build their own sovereign intelligence lab. A place to operationalize their knowledge, replay real work, and optimize agents against the outcomes that matter to their business. Where production experience compounds into intelligence the organization owns.
We’re starting with NeoEval, our automated evaluation engine. It turns your production data into evaluation environments - that dynamically evolves along with your users, workflows, and frontier. A playground for evaluating and optimizing your agents.
Your production data is already a goldmine of real tasks, failures, and human corrections. It captures judgment about what a successful outcome requires and over time this judgement encodes into institutional knowledge. NeoEval, our flagship evaluation engine, turns that experience into evaluation environments grounded in your real tasks, workflows, and edge cases. Where you can replay your agent in your environment. Evaluate and optimize against the metrics that matter to your business. That’s the foundation of your own intelligence lab - where production experience compounds into better outcomes and intelligence you own.
Your data. Your institutional knowledge. Now operationalized into evals and compounding intelligence.
NeoSigma is a product-driven research lab building infrastructure for systems that improve over time. Our founders have worked across foundation model research and agent infrastructure. Gauri was on the founding team at Parallel, where she built deep research agent infrastructure that scaled to millions of users and led core evals at Parallel, with prior research work in foundation models at Apple and MIT. Ritvik previously led foundation model training, data and evals at Essential AI for code and math models.
We’re a team of researchers, engineers, and designers who are deeply technical and passionate about pushing the frontier of agentic systems and redefining how humans and AI work together. We care about creating a fast-moving high agency culture, and more than half of the team are former founders.
We’re fortunate to have the support of investors and leaders across the AI ecosystem from OpenAI, Google DeepMind, Cognition, World Labs, Mercor, Baseten, Fireworks, and others. We’re already working with AI native technology companies and large enterprises and powering the evaluation and optimization layer for their agents.
If our mission sounds interesting to you - we'd love to hear from you. Join us!.