Every case becomes a training environment, not a static dataset.

A real financial situation is rebuilt into a set of graded tasks a model can act in and be scored on, with rewards that check against the record. How that rebuild happens stays in-house, but the controls that make it trainable do not. What reaches a model is the judgment of people who have actually carried the risk.

The asymmetry

A model can be checked. A market never offered to. Code got smart because every answer has a verifier: the tests pass or they do not. Finance never had that signal for the judgment call itself: nothing checked how a decision was reached against what later happened, so it had no automatic way to know when it was right.

The ceiling

So finance trained on opinion. With no objective checker, the best you can learn from is consensus. And consensus caps you at average. You cannot beat the market by memorizing it.

The mechanism

Every deal is an environment. Its outcome is the reward. A real deal already holds the missing signal: what actually happened. Frame it as a problem to solve, and the realized result becomes the reward: the model trains against truth, not against opinion.

The controls

01 — Verifiable reward. Each task is graded against evidence in the record, so the signal a model trains on is defensible rather than a matter of taste.

02 — Point-in-time by construction. A model sees only what was knowable at the moment of decision. The outcome is held back, so there is no hindsight to reward.

03 — Authored by practitioners. Environments are designed and adjudicated by analysts who have worked these situations, and admitted only once they clear that bar.

Seven modes of reasoning

Each task targets a capability frontier models still lack. The modes isolate distinct kinds of judgment, drawn from how our analysts actually work a problem.

Every task is authored in one of seven modes of reasoning — strategic, diagnostic, and quantitative among them. Across all seven, the rubric rewards reasoning that holds up against what actually happened, not against consensus opinion.

The website shows the framework; the artifact carries the recipe.

The full taxonomy, and the discipline each mode encodes, is available under evaluation agreement.

If you are training on finance data, or you have deals to put to work, we will scope it with you directly.

Connect with us