Questions a model team tends to ask first.

—What is an environment, concretely?

A real deal, rebuilt as a set of graded tasks a model acts in and is scored on. Long horizons, primary documents, the tools an analyst uses, and an outcome that can be checked against the record.

—Markets are noisy. How can an outcome be a reward?

The task is framed at the moment of decision and graded on the reasoning that was defensible then, not only on the dollars that followed. A sound call that lost money still scores. A lucky one does not.

—How do you keep the answer from leaking into the eval?

Point-in-time by construction. A model sees only what was knowable at the anchor, the outcome is held back, and the framing is checked for the tells that quietly hand over an answer.

—Can the grader be gamed?

We assume yes until an attack log says otherwise. Every grader is attacked before its task ships — documents stripped, the stem checked for arithmetic that hands back its own answer — and the log ships with the artifact, including the attempts that succeeded. The method is published in our research.

—Why finance, and not code or math?

Code and math already have verifiers, so models compounded there. Finance’s new question-answering benchmarks check answers; nothing yet verifies the judgment behind a decision against what actually happened. Closing that gap is the whole company.

—Who actually builds these?

People who have carried the risk, not an annotation farm. Quality data is downstream of quality judgment, so the framework comes from practitioners before a single task is written.

—What do we actually receive, and where does it run?

Artifacts delivered into your perimeter — the environment, its graders, and the evidence pack behind every claim — dropped into your own training stack. We host sealed evaluations; your training never touches our infrastructure.