Skip to content
JevDirectory.org
Patterns

Normalization

Scaling each Score by its number of levels — dividing by len(criteria) - 1 — before weighting it in a composite.

Open docs.typesafe.aiAll 117 terms
Category
Patterns
Also known as
—
Related terms
3
Directory entries
2
Docs
docs.typesafe.ai
Added
2026-09-24

Definition

Scores from different rubrics are not directly comparable: a 1.43 on a three-level scale and a 3.5 on a five-level scale mean different things. Composite scoring normalizes each by its top level so weights represent relative importance rather than rubric size.

The arithmetic stays in code. Jev's Score levels are weak at numeric calibration, so normalization is a bookkeeping step, not a correction for a measured magnitude.

Tagspatternsscoreevaluation

Related terms

Definitions that connect to this one.

Composite scoringBreak a judgment into atomic Score questions, normalize each, and combine them with weights you control in code.PatternsWeighted scoreThe Score answer computed as each level number times its probability, which is why a score can land between two levels.Answers & ConfidenceScore levelOne entry in a Score's ordered criteria list; levels are numbered by array position from 0 and judged independently.Primitives

From the directory

Pattern: Composite Scoring
Break a judgment into atomic Score questions, normalize each by its top level, and combine them with weights you control in code, as in the resume example's four scored dimensions.
Practices & PatternsDocs#official#patterns#score
Official
Cookbook: Pre-Parsed Value Extraction
Regex finds candidate emails, phone numbers, and amounts; Jev picks the requested span so code copies a verbatim value that cannot be invented, with no free-text extraction required.
Cookbooks & DemosDocs#official#cookbook#extraction
Official

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

LLMs generate answers, Jev makes decisions

Paarangat
Paarangat
@paarangatrai
·

this is the easiest way to understand Jev: LLMs generate answers. Jev makes decisions. that sounds like a small difference, but it actually changes the entire use case. say you give a normal LLM this: “here’s a user, their account history, payment behavior, support chats, Show more

Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 82 replies

Arbitrary classification as a primitive

cocktail peanut
cocktail peanut
@cocktailpeanut
·

Jev is cool not because it re-invented classification, but because it makes ARBITRARY classification into a type-safe programmable primitive. A general purpose zero shot decision model whose native interface is RUNTIME-DEFINED typed decisions, optimized for that exact interface

Image
cocktail peanut
cocktail peanut
@cocktailpeanut

If you called Yann LeCun an idiot for saying we need to move beyond LLMs and build something new, you are banned from using Jev.

Reply
Read 13 replies

How Jev makes agents faster and cheaper

500 emails for 3.5 cents

Headless Chromium agent

Custom Jev-style models for agent workflows

Scott Williams
Scott Williams
@swill1ams
·

Prediction: millionaires will be made using custom Jev style models (parallel constrained decoding) to make the agent systems companies already run more token efficient. Let me explain with a scenario: Imagine a company already has an agent workflow running where an llm reviews Show more

Harsha Gundala
Harsha Gundala
@harshagundal

They were building in stealth for 2 years, I was building in stealth for 2 hours… Happy to open source Qwen-2.5-1B-RLCD, 5x faster on-device inference for JSON workloads that need to be type-safe. ⚡️Demo below on a M4 MacBook⚡️ every LLM has the ability to efficiently batch

Watch on X
Reply
Read 35 replies