Skip to content
All studies

What changes when a model returns a typed judgment?

A local lab for exploring typed answers, probabilities and policy in authored business cases.

Status

The lab puts a typed Jev judgment and its probability beside the policy code that acts on it, so each can be inspected on its own, using synthetic business cases.

In practice

Keep a model’s judgment and the policy that acts on it separate, so each can be inspected.

Why this question matters

A model judgment still needs a policy around it. Typed answers and probabilities make that handoff concrete enough to inspect in code.

What I built

A teaching and experiment workbench around TypeSafe’s Jev judgment model, with synthetic cases and inspectable decision records.

A design choice

The model judges and code decides. Approval, evidence expiry and authority checks stay in code, so withdrawing approval holds the simulated action without a new model call. Letting the model’s answer trigger the action would be shorter, but a confident answer can still be wrong. The lab includes a deliberately confident, wrong example to show it.

Where the evidence stops

An experimental workbench. Authored cases and owner-recorded observations do not establish business ROI or production readiness.

Read the repository