Screen a folder of CVs with the TypeSafe Jev decision model: typed judgments, an editable policy, free re-scoring.
Applications — page 9
Complete applications where Jev makes a product decision: routing, ranking, classification or approval.
2,602 active projects in this collection. All collections →
Can a decision model beat dedicated rerankers? TypeSafe Jev vs Cohere Rerank 4 vs ZeroEntropy zerank-2 vs a chat-model baseline: 14 datasets, every raw API response, bootstrap ranges on every gap.
Converts Command Code API to OpenAI chat completions
No project description available.
Search engine experimentation on the TREC collections. Currently focused on zero-shot reranking implementations with typesafe.ai's JEV model
8
PowerShell decisions with TypeSafe AI's Jev model: https://typesafe.ai/blog/introducing-system-one-models-and-jev
DeepSeek + TypeSafe JEV 微信回复助手：Windows 正式版、Apple Silicon macOS 预览版；本地 OCR 与人工可控回复
Trying to combine Jev with ontology
Use local and hosted classifiers aka decision models aka Jev-like models, all through a single TypeSafe API
TypeSafe Jev (System One) にブラウザ上のマインスイーパーを解かせるデモ
Route each Codex turn to the cheapest model that can handle it, judged by TypeSafe Jev.
No project description available.
8
Your links, loaded before the click.
8
Ask a yes/no question of every function in a codebase. Ranked answers in seconds, for cents. Grep whose pattern is a question, powered by TypeSafe Jev.
8
No project description available.
Grade page sections for clarity, writing and on-page SEO. WXT + TypeSafe AI Jev.
8
Auto approve mode for Pi and Antigravity
7
Use Jev everywhere to make & track decisions
7
Kotlin Multiplatform client for Jev that returns your own enum/sealed types instead of string keys.
Fast zero-shot and few-shot LLM routing powered by Jev.
7
turn any llama-server into a jev system one endpoint
7
No project description available.
Run a JSON Schema through TypeSafe's Jev API, and get JSON back.
JevNoiseGate filters unwanted notifications and SMS on Android. Rather than matching keywords, an LLM decides what's noise — and only what it explicitly flags is blocked. Verification codes are matched on-device and never uploaded; anything uncertain passes through.