Jev in production › Message and ticket triage

jev-oncall

One Jev call per alert scores actionability, severity, owner and duplicates for incident triage; a demo shows a 0.87-matched duplicate routed to review instead of paging (jev-oncall).

Open on GitHub ↗

0.87measured, as published by the source
Use
Message and ticket triage
Industry
IT operations
Form
Open-source tool
Stage
Announced
Listed
2026-09-26
Found via
discord
Repository
mingleiw/jev-oncall
Stars
4
Forks
0
Last push
2026-09-29
Language
HTML
License
MIT
jev-oncall screenshot
docs/architecture.png in the mingleiw/jev-oncall README, MIT; shown from GitHub.

The README opens with

On-call tooling built on Jev, TypeSafe's System One decision model, with one rule throughout: the model judges, plain code decides. Jev answers narrow, typed questions with probabilities; auditable code turns them into actions.

- Root-cause analysis (current focus): can Jev find why an outage happened, with no general-purpose LLM in the loop? An open benchmark on recorded incidents and on outages adapted from public postmortems, with every trace committed. - Alert triage: route each production alert (page, review, ticket or drop) and link symptoms to their cause. A working server with a live demo.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for message and ticket triage