Jev directory
CommunityJev Demos & Experiments
Otimizador Jev
Portuguese-language Google Colab notebook that routes delivery support tickets with Jev's Score and Choice primitives, turning report text, user history, and financial volume into a 1-10 complexity index and a deterministic lane choice.
- Stars
- 0
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Notebook models a support triage engine with Jev Score and Choice primitives.
- Score maps report text, user history, and financial volume to a 1-10 complexity index.
- Choice routes each ticket deterministically to a lane based on that complexity value.
- The feasibility study reports Jev answering about 160 times faster than a conventional LLM.
- Runs in Google Colab by executing the notebook cells in sequence.
Questions about this entry
Short answers drawn from the linked project or page.
Open the notebook file in Google Colab and execute the cells in sequence: the first cells initialize the Jev engine, the next load the scenario dataset, and the final cells render the operations dashboard with performance charts.
Score evaluates the unstructured report body, the user's history, and financial volume, converting them into a linear complexity index from 1 to 10 that drives the rest of the pipeline.
Choice performs deterministic routing, selecting the destination lane immediately from the complexity value produced by Score, so identical inputs map to the same lane.
It uses a simulated dataset of everyday delivery support reports, including missing items, packaging problems, and users with a high number of recent tickets, isolating variables so the logic engine can be audited.
The feasibility study compares Jev with a commercial generative LLM such as GPT-4o per 1 million requests and reports Jev responding roughly 160 times faster, with a sharp reduction in cost per call.
The project is written in Portuguese and delivered as a Python notebook designed for Google Colab, consolidating actions and metrics into a structured dataframe for management review.
It is a simulation and feasibility study over synthetic delivery tickets rather than a production support system; the material describes no deployment, authentication, or live integration with a ticketing platform.
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
Spanish-language prototype that uses Jev to classify event sign-ups and decide program, action, and message before sending, with a guardrail that approves, flags, or blocks outgoing text. Includes synthetic datasets, evaluation scripts, and a local engine that runs without a key.
Jev Demos & Experiments#madewithjev#demo#python
Communityblockstars-labs/30x-JEV
A Python demo that screens PubMed abstracts for one systematic review question using Jev. Six narrow questions per abstract go to Jev in a single call, with rule-based tiers and confidence gates deciding include, exclude, or human review.
Jev Demos & Experiments#demo#python#madewithjev
Communityanondo1969/jev-evidence-triage
A small Go web app that scores 200 catalog emojis against a line of group-chat text with TypeSafe Jev, then shows the fitting ones as read-only reactions. Ships as a single static binary and a scratch Docker image, and needs a TypeSafe API key.
Jev Demos & Experiments#madewithjev#demo#classification
Communityamscotti/jevmoji
Privacy-first Next.js app that sorts saved X bookmarks into Top picks, Needs human look, and Skip using one Jev call per bookmark. Composite scoring, confidence-gated routing, and a deterministic mock mode that runs without an API key.
Jev Demos & Experiments#demo#typescript#routing
CommunityPirozshki/jev-bookmark-triage
Browser and terminal demo that ranks emoji against a free-text query by sending one Jev score question per emoji, then filtering by a tunable score floor and limit. Includes a bench harness over saved queries.
Jev Demos & Experiments#madewithjev#demo#typescript
Communitynischal94/emoji-sift
A runnable incident-routing example that keeps exact facts, model judgment, policy and human review separate: a registry assigns known assets deterministically, and Jev answers choice, score and noul questions only when the input is messy.
Jev Demos & Experiments#community#python#incidents
From 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.