Skip to content

Jev glossary

Core ConceptsStructured output

Typed decision

A model output that conforms to a software type your code expects, rather than free-form text that has to be parsed.
Category
Core Concepts
Also known as
Structured output
Reading time
1 min
Related terms
4
Directory entries
2
Docs
docs.typesafe.ai
Added
2026-09-24

Definition

System One is type-safe by construction: decisions and probabilities conform to the structured types and JSON schema your code expects. The model returns a distribution over the options you supplied, never a value outside the schema.

Typed decisions are what make Jev composable. They can be compared, thresholded, sorted, stored, and fed into further logic (or into a classical ML model) without the parsing layer that text generation requires.

Tagscorearchitecture

From the Jev directory

Directory entries that go deeper on this term.

The idea behind Jev: models that return typed decisions and probabilities instead of generated text, named after Kahneman's fast-thinking System 1, with confidence to route around uncertainty.
Jev Guides & ArticlesDocs#official#docs#architecture
Official
Design AI-powered software by keeping code in control and giving System One narrow, structured decisions to make.
Jev Practices & PatternsDocs#official#patterns#architecture
Official

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai