Automated README summary
Automatically summarized from the README on 29 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A community-maintained .NET client library for the TypeSafe AI System One HTTP API. It lets C# developers ask typed yes/no, choice, and score questions about text or JSON state and receive structured, confidence-scored answers. Not affiliated with TypeSafe AI.
How it uses Jev
The SDK sends NoulQuestion (yes/no), ChoiceQuestion (pick one label), and ScoreQuestion (position on a rubric) to the System One API. Results are exposed as NoulAnswer.Probability, ChoiceAnswer.Label, and ScoreAnswer.Score, with confidence and probability distributions surfaced verbatim for routing or scoring in code.
Primitives:noulchoicescore
Technique worth stealing
Fan out many typed questions in one round trip against the same state, then gate routing on reported confidence.
Try it
dotnet add package TypeSafeAI.Sdk --prerelease, set TYPESAFE_API_KEY, then call client.SystemOneAsync with questions.
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 material0.75
- Shows a System One patternnot found in the excerpt0.07
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.06
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.03 / 2
- About JevFound in material0.86
no-judgment band (0.40–0.60)
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 29 Oct 2026.