typesafe-triage-guard

Three composable judgment pipelines on TypeSafe's Jev: support-ticket triage, observability alert triage, and a deploy-risk gate.

How it uses Jev

Three composable judgment pipelines built on TypeSafe's System One model, Jev — a model that returns typed, calibrated probabilities instead of generated text. This repo is R&D / a worked example, not a product: it exists to test what the TypeSafe primitives (Noul, Choice, Score) are actually good for outside the docs' own demos, across three different domains, with one shared architecture.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to typesafe-triage-guard

Browse all
semdecide project preview
Applications
Typed semantic decisions for Unix pipelines and CI, powered by TypeSafe AI Jev.
JevTicktRouter project preview
Applications
A .NET 10 and React 19 application for fast, structured AI-powered ticket triage using TypeSafe Jev.
twitter-jev-guard project preview
Applications
使用 TypeSafe Jev 在 X/Twitter 时间线上识别低质量、垃圾和广告帖子,并在文字区域显示醒目的半透明水印。
daf-jev project preview
Benchmarks & research
daf-jev: composable Python toolkit for TypeSafe's Jev (System One) decision API — question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill
NanoJev project preview
Benchmarks & research
A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.
lanebreak project preview
Demos & playgrounds
LaneBreak — support ticket priority+routing via TypeSafe Jev
jev-guard (klauswg) project preview
Agent tooling
Real-time risk triage gateway for exchange deposits and withdrawals — Jev (TypeSafe System One) handles triage only; adjudication stays in deterministic code.
pi-jev-code project preview
Agent tooling
Single-agent Pi coding coprocessor with Jev semantic gates, baseline-to-current diff review, and append-only observability telemetry.
jev-benchmarks project preview
Benchmarks & research
Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.