Automated README summary
Automatically summarized from the README on 1 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Kassad is a .NET library that sits between your application and the language model, running prompts, completions, tool calls, and citations past typed checks to produce Allow/Flag/Review/Block verdicts for your code to act on.
How it uses Jev
Jev answers typed questions (Noul/Choice/Score) about extracted state such as user_message, system_prompt, completion, tool arguments, or claim/source pairs. The returned calibrated probabilities are thresholded by policy to produce a verdict with probability and confidence, which your code uses to allow, flag, review, or block.
Primitives:noulchoicescore
Technique worth stealing
Batch all policies for a stage into one request, so ten checks cost one round trip.
Try it
dotnet add package Kassad.AspNetCore; dotnet add package Kassad.TypeSafe; run the sample with TYPESAFE_API_KEY.
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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 material0.66
- Shows a System One patternFound in material0.94
- Describes handling uncertaintynot found in the excerpt0.09
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.93
- Top-10 learning shortlist signalnot found in the excerpt0.36
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.31 / 2
- About JevFound in material0.97
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 1 Oct 2026.