Why not just use regex or a chat model prompt?

Hand-rolled regex breaks on phrasing variants and LLM text needs parsing, retries, and confidence guessing. Here you declare the answer space and get values plus calibrated confidence your code can branch on.

How do custom C# types survive the round trip?

Pass plain objects, enums, or records and each option is sent as its JSON description. Answers map back to the exact instances you supplied, including members never sent to the model.

Can I ask several questions in one request?

Create immutable questions once with the factory, attach several to one query, and read each answer back with the same handle. Questions evaluate in parallel against the same state.

Will this run on older Framework projects?

Yes. It targets .NET Standard 2.0 with System.Text.Json as the only dependency. Pass your own HttpClient if you need custom handling; otherwise the client owns its own.

What options can I set on the client?

SystemOneOptions carries Endpoint, defaulting to https://api.typesafe.ai/v1/systemone, Model defaulting to jev-latest, and MaxChoiceProperties, 20 by default, which caps how many serialized properties one choice option may contain. The options are immutable and validated once.

How do I read a Noul answer, and is it a bool?

NoulAnswer.Noul is the probability that the answer is yes, from 0 to 1, and there is no automatic boolean conversion, so you choose the threshold yourself. Confidence on a Choice or Score lets you act automatically when the model is sure and escalate when it is not.

How do custom option types map back to my instances?

ChoiceAsync accepts POCOs, enums or records; each option is sent as its JSON description with deterministic ids, and the answer maps back to the exact instance you supplied, including members marked JsonIgnore that were never sent. Strings stay strings and enums serialize by name.

CommunityJev Repos & SDKs

SystemOneDotNet

.NET client for System One where you declare choice, score, and yes-or-no questions in C# and get typed answers with probabilities and confidence back, installable as one NuGet package.

See highlights

Open github.com

Stars: 4
Language: C#
License: MIT
Published by: Community
Author: JabbaKadabra
Last verified: Oct 2026

JabbaKadabra/SystemOneDotNet

User repository on GitHub

View on GitHub

.NET client for TypeSafe System One (Jev) — typed questions in, typed answers with probabilities and confidence out. No prompt engineering, no output parsing.

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Structured AI decisions for .NET — no prompt engineering, no output parsing. SystemOneDotNet is the .NET client for TypeSafe System One, the class of models that Jev belongs to. System One models do not write prose. They evaluate a state against typed questions and return decisions, probabilities, and calibrated confidence that your code can branch on directly:

Quoted from the project's README. Read the full README.

Tagscommunity awesomejev catalog-import

Works forJev for Classification

Used inJev for Software & DevTools

Languages: C# / .NET

Highlights

Choice, score, and yes-or-no answers arrive as typed C# values with distributions.
Batch several questions per request; they evaluate in parallel on the same state.
Options can be records or enums serialized as JSON with exact-instance mapping.
Confidence-first pattern: act when sure, escalate to a human when not.

Watch out

You still need a TypeSafe key and must pick your own confidence thresholds per workload. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

typesafe-sdk-dotnet

.NET port of the JavaScript SDK that batches Choice, Score, and Noul questions in one call, resolved by explicit options, environment, then defaults.

Jev Repos & SDKs#community#awesomejev#catalog-import

Community

hardkoded/typesafe-sdk-dotnetC#

ElBruno.AI.Jev

A community-maintained .NET 10 client for the official TypeSafe Jev API, covering the Choice, Score and Noul primitives with Microsoft.Extensions.AI composition, model discovery and ten runnable samples. Released as tentative 0.6.0 with live compatibility unverified.

Jev Repos & SDKs#community#awesomejev#catalog-import

Community

elbruno/ElBruno.AI.JevC#

jev-net

A C# client for the TypeSafe System One API with one dependency, a faithful port of the official Python SDK's behaviour, and typed answers bound to properties by name.

Jev Repos & SDKs#community#awesomejev#catalog-import

Community

brightshore/jev-netC#

TypeSafe.Jev

C# client for Jev, TypeSafe AI's System One model. Typed Noul, Choice and Score questions go out with one state in a single round trip and come back with a value, a probability distribution and a confidence number. Choice questions can be built from an enum, so the compiler finds the switch branch you forgot.

Jev Repos & SDKs#community#awesomejev#catalog-import

Community

RavenValentin/TypeSafe.JevC#

go-jev

Go SDK plus a pipeline-friendly CLI for typed decisions, covering single questions, batched question maps, retries, and line-oriented filtering over stdin.

Jev Repos & SDKs#community#jevbest#catalog-import

Community

mattn/go-jevGo

swift-jev

Swift library and CLI for asking Jev typed Choice, Noul, and Score questions from Apple platforms, with answers returned alongside calibrated probabilities in one parallel request.

Jev Repos & SDKs#community#jevbest#catalog-import

Community

d-date/swift-jevSwift

From the Jev guides

Original write-ups on what this entry is for.

The Open Reimplementations: Local Models That Speak System One

Sep 22, 2026

Closed weights have not stopped the ecosystem from rebuilding the shape in the open. API-compatible servers, retrained heads on small models, and inference-time tricks that skip generation entirely.

Jev Repos & SDKs#open-models#research#local

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai