Skip to content
JevDirectory.org
Answers & ConfidenceScore expectation

Weighted score

The Score answer computed as each level number times its probability, which is why a score can land between two levels.

Open docs.typesafe.aiAll 117 terms
Category
Answers & Confidence
Also known as
Score expectation
Related terms
5
Directory entries
2
Docs
docs.typesafe.ai
Added
2026-09-24

Definition

A Score of 1.43 on a three-level rubric means the probability sat mostly on level 1 with some on level 2. The value is an expectation over levels, not a measurement of a real-world magnitude.

The jaggedness page is direct about this: do not interpolate between levels to reconstruct an exact number. Use the weighted score to compare against a threshold, and keep arithmetic in code.

Tagsconfidenceprimitives

Related terms

Definitions that connect to this one.

ScoreRate the state against 2 to 10 ordered levels; returns a probability-weighted position, per-level probabilities, and confidence.PrimitivesScore levelOne entry in a Score's ordered criteria list; levels are numbered by array position from 0 and judged independently.PrimitivesScore legendThe Score answer field that maps each level number back to its description, so results stay readable after the fact.PrimitivesUnreliable countingJev does not count reliably — characters, occurrences, or list items — and error grows with the size of the thing counted.Evaluation & TrainingComposite scoringBreak a judgment into atomic Score questions, normalize each, and combine them with weights you control in code.Patterns

From the directory

Score
Rate content against 2 to 10 ordered levels. Returns a probability-weighted score that can land between levels, per-level probabilities, and confidence, with the arithmetic left to code.
Practices & PatternsDocs#official#primitives#score
Official
Jev 1.13 Jaggedness
A maintained list of jev-1.13's known failure modes, literal reading, unreliable counting, dates as text, indirection, context rot, and contradictory criteria, each with a guardrail.
Practices & PatternsDocs#official#docs#evaluation
Official

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

1,891 ads in 19 seconds

ares. 🎧
ares. 🎧
Humalike
@aresotik
·

ESTA HERRAMIENTA ACABA DE ROMPER TODO EL MERCADO DEL AD SPY Maxfusion ha cogido JEV, el modelo nuevo de TypeSafe, y le ha metido la ad library entera de una marca → 1.891 anuncios clasificados → 19 segundos → 0,12 $ Y no es un resumen: cada anuncio etiquetado por etapa del Show more

Watch on X
Ori Silver
Ori Silver
@OriSilver

JEV makes competitor research feel like a cheat code We fed it Resilia’s ad library and it classified 1,891 ads in 19 seconds for $0.12 Customer journey stage, ad style, and a full account deep dive Coming soon to the maxfusion MCP

Watch on X
Reply
Read 12 replies

Game levels generated in real time

900 images in 40 seconds

Intent-based search in Gmail

nader dabit
nader dabit
Cognition
@dabit3
·

Jev is really good at intent-based search! How it looks in Gmail: (for a huge inbox you'd prob let semantic search / embeddings pull first but still much better experience)

Watch on X
nader dabit
nader dabit
Cognition
@dabit3

Another crazy @typesafeai Jev example: Predictive spreadsheets Spreadsheets recalculate numbers, not meaning. Jev reads intent. Type "Urgency" at the top of a column and, as you type, it figures out you want each row rated from "no follow-up needed" to "urgent" in ~100 ms.

Watch on X
Reply
Read 44 replies

End-to-end tests run by agents

An always-on assistant with no wake word