raushankumar035/customer-support-traige-with-jev-
User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Customer Support Triage with Jev (Raushankumar035)
A small FastAPI demo that triages customer support tickets with Jev as the decision layer: one request returns typed answers for department, urgency, refund intent and human-review need, while Python rules route and LangChain can draft a reply.
- Stars
- 0
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- Raushankumar035
- Last verified
- Oct 2026
Used inJev for Customer Support
Highlights
- Three layers: Jev decides the ticket's department, urgency, refund intent and human-review need; plain Python routes; LangChain optionally drafts the reply.
- One Jev request asks four typed questions: department as a choice, urgency as a score and two probabilities.
- Deterministic routing lives in choose_route so business rules stay auditable and are never left to an LLM.
- Graceful degradation: if Groq is missing or fails, the Jev results still render in the dark-theme UI.
- Optional replies are told never to promise refunds, credits or fixes and to mention escalation to a human.
Watch out
README and GitHub metadata reviewed 2026-10-17; the excerpt ends inside the feature list, so the API shape, run instructions, example tickets and license are not available, and no benchmarks or pricing are shown.
Questions about this entry
Short answers drawn from the linked project or page.
A small FastAPI demo that classifies support tickets with Jev as the decision layer, routes them with plain Python business rules, and can draft a customer reply with LangChain and Groq.
One Jev request asks four typed questions: department as a choice, urgency as a score, and refund-related and human-review-needed as probabilities, all returned as typed answers.
The design keeps decisions with Jev and the final route with deterministic code in choose_route, so business rules stay auditable and are never left to an LLM.
When Groq is configured, LangChain drafts a short reply that is told never to promise refunds, credits or fixes, and to mention escalation when the ticket goes to a human.
The demo degrades gracefully: if Groq is missing or its call fails, the Jev results still render, so classification and routing do not depend on the drafting layer.
The README describes a clean dark-theme UI with one-click example tickets; the digest excerpt does not include screenshots, so the actual layout cannot be reviewed here.
The excerpt ends inside the feature list, so install and run steps, the API endpoints, license information and example tickets beyond the description are unavailable for review.
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 repository whose name and README heading promise customer support triage built with Jev. As of 2026-10-17 the repository has only a title README, but it is notable for its 6 forks against 4 stars.
Jev Demos & Experiments#community#github#python
A 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/jevPythonScaffold project for implementing Jev as a gateway integration layer, demonstrated by a FastAPI service that answers weather questions for a City/State: an SLM works out intent, location and date, Open-Meteo supplies facts, and an LLM writes the answer.
Jev Demos & Experiments#community#github#python
Community
rogerwtrimble-tech/jevPython
rogerwtrimble-tech/jevPythonTwo runnable demo apps that send identical typed questions to OpenAI Decisions (gpt-6-luna) and TypeSafe Jev (jev-latest) in parallel: a support ticket router over 20 labelled tickets and a cloud alert triage over 15 labelled alerts, with thresholds in plain Python making the final calls.
Jev Demos & Experiments#community#comparison#fastapi
An 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.