Domains: valuation · underwriting · risk · structuring · markets.

—Reinforcement learning

Durable environments where real financial work happens: long horizons, primary documents, the tools an analyst actually uses, and an outcome that can be checked. This is reinforcement learning with verifiable rewards (RLVR), applied to finance. We preserve the full complexity of each deal, and that bar does not move as the corpus grows.

—Long-horizon deals

Underwriting that unfolds over days, through ambiguity, dead ends, and revision. We capture work that reflects how real diligence happens while preserving the signal needed to improve a model.

—Benchmarks and evals

Quality is easy to reduce to the wrong metric. Our evaluations grade judgment against the record — sealed task sets, decomposed scoring, and the full transcript behind every claim. Reference results are published in our research; full reports are available under evaluation agreement.

—Off-the-shelf datasets (coming soon)

Prebuilt finance corpora, curated for signal and reviewed by practitioners, structured to drop into your training stack without translation work.

—Supervised fine-tuning on analyst trajectories (coming soon)

Full traces of how an expert works a deal: the documents pulled, the model built, the calls reversed, the thesis defended. Demonstrations that set the right prior, so models learn the shape of the work, not just the finished answer.