sarikainnovate-code/jev-decision-desk
User repository on GitHub
Confidence-aware decision routing with Jev, Streamlit, and deterministic guardrails.
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Jev Decision Desk
A standalone proof of concept showing Jev as a structured decision layer for support-ticket routing: fixed-option routing, 1–5 urgency scoring and probabilities for sensitive data, with a deterministic confidence and safety policy deciding auto-route versus human review.
- Stars
- 0
- Language
- Python
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- sarikainnovate-code
- Last verified
- Oct 2026
Highlights
- Fixed-option routing to Payments, Access, Security, Product or General, plus urgency scoring from 1 to 5.
- Returns probabilities for sensitive data and safe automation; a deterministic policy auto-routes only when confidence and safety conditions pass.
- Application code, not generated prose, controls the final action; the model evaluates narrowly scoped decisions.
- Shows a visible decision trace and API-request preview; mock mode runs with no credentials.
- Live mode uses the TypeSafe System One API and jev-latest; MIT licensed, created and pushed 2026-10-03.
Quickstart
bash
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
streamlit run app.pyWatch out
README and GitHub metadata reviewed 2026-10-17; the digest truncates the enable-Jev section mid-command, so the full live-mode setup and any accuracy checks are not captured. The README says it uses fictional data and is not connected to any existing project.
Questions about this entry
Short answers drawn from the linked project or page.
A standalone proof of concept that shows Jev acting as a structured decision layer for support-ticket routing, using fictional data and deterministic guardrails for confidence-aware decisions.
Choice routing to Payments, Access, Security, Product or General; urgency scoring from 1 to 5; and probabilities for sensitive data and safe automation.
Application code does. The model evaluates narrowly scoped decisions, and a deterministic confidence and safety policy turns them into auto-route or human review; generated prose never controls the action.
Yes, mock mode requires no credentials; the README tells you to create a venv, install requirements and run the Streamlit app locally.
Create an API key with TypeSafe AI, store it in the TYPESAFE_API_KEY environment variable, and run the app; live mode calls the TypeSafe System One API with jev-latest.
No. The README says it uses fictional data and is not connected to any existing project — it is a proof of concept for the decision pattern.
MIT, Python, 0 stars, created and pushed 2026-10-03, with a built-in decision trace and API-request preview.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Facebook: Intake Router keeps diagnosis out of the answer space at the front desk.
FacebookClinicnotes
X: OpenRouter Decision Model Rankings
X: herdr + jev, an agent router
X: A group chat bot with decision room routing
More Jev resources like this
A Chinese-language e-commerce customer-service demo on FastAPI, LangGraph and React: adaptive retrieval routing with hybrid BM25-plus-vector search, and intent classification switchable between TypeSafe Jev's structured choice interface and DeepSeek.
Jev Demos & Experiments#community#github#python
Community
gbh1234/Adaptive-ragPython
gbh1234/Adaptive-ragPythonA Python web app that sends every support ticket to Jev (typesafe/jev-1.13) and to configured comparison models through OpenRouter, showing team routing, urgency, severity, sentiment and draft replies side by side with latency and cost.
Jev Demos & Experiments#community#github#python
Community
nikojim/jevPython
nikojim/jevPythonA browser playground for S1-CED, a small decision model you give a piece of text plus typed questions — yes/no, which-of, or a 0-3 score — and it answers with a probability per option and whether it is confident enough to act or a human should check. Runs on CPU; no GPU or account needed.
Jev Demos & Experiments#community#github#python
Community
ai-yatra/s1ced-playgroundPython
ai-yatra/s1ced-playgroundPythonA Streamlit lab that places a bounded System One decision inside a coding-agent workflow: Laya classifies CI failures, LangGraph applies a fallback policy, and an OpenAI agent inspects a fixture repo and proposes a fix.
Jev Demos & Experiments#community#github#python
Community
natenberenstein/systemonePython
natenberenstein/systemonePythonA proof-of-concept HTTP service for constrained decisions with a local MLX model: send text or JSON plus typed choice, score, or noul questions and it returns probabilities over the answers you declared — no generated text, no parsed model JSON.
Jev Tools & CLIs#community#github#python
Community
snellingio/system-onePython
snellingio/system-onePythonAn open-source browser 3D character split between two models: GPT-Live-1 talks with you over WebRTC while Jev reads the live transcript and picks Annie's face, gestures and body language in about 120 ms, with code gates on every answer.
Jev Demos & Experiments#community#github#python
Community
rehan-remade/open-anniePython
rehan-remade/open-anniePythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.