Primitives· Last updated

Jev confidence vs probability

Probability is the mass on each option or level. Confidence (Choice and Score only) collapses the shape of that distribution into one number in [0, 1].

A peaked distribution → high confidence. A flat one → low confidence. TypeSafe computes this for you. Their confidence page’s three-option demo uses the approximation (3 × largest probability − 1) / 2. They also say you are not locked into their definition: the full probabilities object is always there if you want another statistic.

Noul is different

Noul has no confidence. Do not invent one. Threshold the noul, or define bands (auto / review / abstain) on the distance from 0.5.

Three paths

TypeSafe’s starting pattern:

  1. High confidence — act automatically.
  2. Medium — confirm, flag, or gather more state.
  3. Low — do not act; route to a human or another system.

Where you draw the lines depends on stakes. Showing a balance at 0.6 confidence is not the same as approving a transfer. Official examples use floors such as 0.5 or 0.6 and higher bars (0.85 or 0.9) for irreversible actions. Those numbers are illustrative. Start conservative and tune on your labels.

Calibration reminder

Higher confidence is trained to mean higher accuracy across groups of predictions. It is not a warranty on the next ticket.

Sources

Public TypeSafe or adjacent documentation only. No private claims.