User repository on GitHub
Generated by code.quarkus.io
- Forks
- 1
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Jevving
A Quarkus proof of concept that dispatches support tickets with Jev: one call answers urgency as a noul, the best-placed team as a choice and severity as a score, and low-confidence tickets go to review instead of being assigned automatically.
- Stars
- 0
- Language
- Java
- Reading time
- 2 min
- Published by
- Community
- Author
- darkwings
- Last verified
- Oct 2026
Used inJev for Customer Support
- Languages
- Java
- Capabilities
- Open source
Highlights
- Proof of concept of a support-ticket dispatcher powered by Jev, generated from code.quarkus.io.
- One Jev call answers three typed questions: urgency as a noul, the team as a choice and severity as a score.
- Severity runs MINOR, MAJOR, BLOCKER; urgency turns URGENT above urgency.limit; low team confidence goes to NEEDS_REVIEW.
- Explicitly not production-ready: state is in memory, teams are hard-coded, and submittedBy is trusted without authentication.
- Java Quarkus project with 0 stars and 1 fork, created and pushed 2026-10-11; no license listed.
Watch out
README and GitHub metadata reviewed 2026-10-17; the captured excerpt ends mid-sentence in the review rules and the warning block is truncated, so setup steps, the urgency threshold value and how the dispatcher runs are not visible to verify.
Questions about this entry
Short answers drawn from the linked project or page.
A proof-of-concept support-ticket dispatcher built with Quarkus and powered by Jev. When a ticket arrives, Jev reads the request and answers typed questions that decide urgency, the handling team and severity.
Three, in a single call: whether the message needs immediate help, as a noul from 0 to 1; which team is best placed to resolve it, as a choice among the support teams; and how serious the problem is, as a score from MINOR through MAJOR to BLOCKER.
It goes to NEEDS_REVIEW when Jev's confidence in the chosen team falls below dispatch.confidence-limit, or when it finds the condition described in the README sentence that is cut off in the captured excerpt.
No. The README warns it is a proof of concept: everything is in memory and tickets are lost on restart, support teams are hard-coded in InMemorySupportTeamRepository, and there is no authentication because submittedBy is trusted from the client.
Jev returns a noul between 0 and 1 for whether the message conveys a need for immediate help; tickets above urgency.limit become URGENT and the rest NORMAL, with the threshold living outside the model.
It is a Java Quarkus project generated from code.quarkus.io, and GitHub shows 1 fork, but the digest does not capture install or run steps, so setup cannot be described here; no license is listed either.
No. The README states there is no API to manage support teams: adding, removing or changing one means editing the code and restarting, which is one of the warnings that marks it as a proof of concept.
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-ragPythonE-commerce customer-service quality sandbox: Jev judges intent, emotion, urgency and risk per message, an 8-rule decision table routes to queues with SLAs, and dangerous agent phrasing is blocked with rewrite suggestions before it is sent.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
kiler398/jev-demoTypeScript
kiler398/jev-demoTypeScriptA 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 learning lab for decision models: TypeSafe Jev and Microsoft Decision-1 route support tickets in under a second for about $0.02 per 1,000 calls, while Claude handles the hard cases. It ships an interactive site, a benchmark, calibration tests and docs.
Jev Demos & Experiments#community#github#benchmark
A Kafka Connect sink connector that sends each input record to TypeSafe AI's Jev with questions you define, then publishes an Enriched Record holding the original message, Jev's answers and the evidence to trace and deduplicate each evaluation.
Jev Integrations & Adapters#community#github#kafka
Community
smatiolids/kafka-jev-connectorJava
smatiolids/kafka-jev-connectorJavaA 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.
Jev Demos & Experiments#community#github#fastapi
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.