User repository on GitHub
jev-demo: Jev decide, el LLM razona. Tres demos para alumnos
- Forks
- 12
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
jev-demo: Jev decide, el LLM razona
Three TypeScript demos built on one pattern for students: Jev answers a typed question with a probability, your code decides what to do, and Claude works only where it is needed. Demos cover Jira triage, pre-flight checks and PR routing.
- Stars
- 10
- Language
- TypeScript
- Reading time
- 2 min
- Published by
- Community
- Author
- SoyJorgePilo
- Last verified
- Oct 2026
Used inJev for Software & DevTools
- Languages
- TypeScript
- Capabilities
- Open sourceRequires API key
Highlights
- One pattern across three demos: state -> typed question -> Jev -> probability -> your code decides -> action.
- Demo 1 triages Jira tickets (type, priority, team, needs-a-human); code applies, marks for review, or escalates.
- Demo 2 pre-flight: Jev flags functions with existing problems before you touch code; Claude explains only the flagged ones.
- Demo 3 routes PRs: rules without an LLM, Haiku, or Sonnet; Claude reviews and comments on GitHub.
- A costs script compares "LLM only" (everything to Sonnet) against "with Jev" in tokens and USD.
Watch out
README and GitHub metadata reviewed 2026-10-17; the README is in Spanish and the excerpt truncates mid-sentence, so setup commands, real credential requirements and the cost numbers are not evidenced here.
Questions about this entry
Short answers drawn from the linked project or page.
A set of three demos for students built on one pattern: estado -> pregunta tipada -> Jev -> probabilidad -> tu código decide -> acción. Jev decides with probabilities and the LLM reasons only where needed.
Three: Jira triage (Jev classifies each ticket and code applies, marks for review or escalates), pre-flight (Jev flags problem functions before coding, Claude explains the flagged ones), and a PR router.
Jev decides which PR goes to rules without an LLM, which goes to Haiku, and which to Sonnet; Claude then reviews and comments on GitHub. A /comparar skill is listed for comparison.
Yes: the README says the demos use real services (Jev, Claude, Jira and GitHub) and that nothing is simulated, so you need your own credentials for the services each demo touches.
It ships a costs script (scripts/costs.ts, with a /costos skill) that reports tokens and USD for each execution, comparing "solo LLM" (everything to Sonnet) against "con Jev"; the digest does not include the resulting figures.
Students, per the repository description: three demos para alumnos that teach the decide-with-Jev / reason-with-LLM division of labour. Everything is in Spanish.
GitHub user SoyJorgePilo published it on 2026-10-14, created and last pushed the same day, with 9 stars and 10 forks; the digest lists no license and no test or packaging details.
More Jev resources like this
A TypeScript SDK demo for Jev, TypeSafe's System One model: 14 numbered scenarios teach how to prepare state, write questions and use answers, with root examples that ask whether a customer message sounds frustrated and flag it for review.
Jev Demos & Experiments#community#github#typescript
Community
gopinav/jev-demoTypeScript
gopinav/jev-demoTypeScriptA demo that has three decision models read recent news and price Polymarket and Kalshi questions, then compares their probabilities with live market odds and replays how each model changed its mind article by article.
Jev Demos & Experiments#community#github#demo
Community
yorkeccak/model-vs-marketTypeScript
yorkeccak/model-vs-marketTypeScriptA 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
Demo pack from the French-language Jev meetup of 8 October 2026 on System One models: a Chrome ad-blocker, an unclutter browser fork, a decision-routing kit comparing a local engine with Jev via OpenRouter, and n8n email triage.
Jev Demos & Experiments#community#github#demos
Community
royam0820/Jev-MeetupJupyter Notebook
royam0820/Jev-MeetupJupyter NotebookA TypeScript starter for Jev called through the Vercel AI Gateway with the AI SDK. It wraps evaluate calls in an askJev helper and ships a support-ticket triage example using choice, score and boolean questions.
Jev Demos & Experiments#community#github#typescript
Community
1leetadmin/JEVTypeScript
1leetadmin/JEVTypeScriptA Next.js workbench for evaluating AI ticket triage with TypeSafe AI: classify, route and score support tickets through structured schemas, then inspect outputs, latency, token use and estimated cost in a three-column view.
Jev Demos & Experiments#community#github#typescript
Community
netflix2023/jevTypeScript
netflix2023/jevTypeScriptFrom 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.