jevbooks

← All projects

jev4s

maxtrezzi/jev4s

Typed Scala client for Jev: typed questions, typed answers, errors as values.

Automated README summary

Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

jev4s is an unofficial Scala client for Jev, the TypeSafe AI 'System One' model. It lets Scala 3 and 2.13 programs send typed questions about their own data and receive typed answers with probabilities, without text generation.

How it uses Jev

The user defines a state (e.g., a Ticket) and a ToState conversion to JSON. They build a named tuple of typed questions (Choice, Score, Noul, Box) referencing state fields. client.ask returns Either[JevError, Answers], where each answer has the type of its question; code matches on the result to make decisions.

Primitives:choicescorenoul

Technique worth stealing

Use Scala 3's type system to make invalid questions and answers compile errors, and return all validation problems as values before sending.

Try it

Add libraryDependencies += "io.github.maxtrezzi" %% "jev4s" % "0.2.0" and call JevClient(config).ask(state, questions).

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.14.0
Project signals
jev-1.14.0
Category
jev-1.14.0
Pattern tags
jev-1.14.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.73
  • Shows a System One patternnot found in the excerpt0.26
  • Describes handling uncertaintynot found in the excerpt0.04
  • Reports measured numbersnot found in the excerpt0.02
  • Is a runnable toolFound in material0.88
  • Top-10 learning shortlist signalunclear0.45
  • Is a replica of the modelnot found in the excerpt0.02
  • Solves a common problem (0–2)score on a 0–2 scale1.00 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.73Shows a System One pattern0.26Describes handling uncertainty0.04Reports measured numbers0.02Is a runnable tool0.88Top-10 learning shortlist signal0.45Is a replica of the model0.0200.51Solves a common problem (0–2)1.00 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.97Inspection0.79Fail open, fail closed0.40Funnel0.36Traffic light0.3400.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 3 Nov 2026.