jev-demo
Next.js and Python demo where one Jev call per email returns spam probability, category and urgency on Enron-Spam.
Overview
JEV email classification demo shows Jev on the public Enron-Spam dataset. Each email gets one Jev call asking three questions at once: is it spam (Noul, scored against dataset labels), which category it belongs to (Choice over marketing, finance, sales, customer support or other), and how urgent it is (Score on an editable five-level rubric).
The Next.js and MUI app has three views: try a single email and inspect the exact request and response, run a balanced dataset sample and explore accuracy and distributions, or view a saved example run without a key. A standalone Python script asks the same questions and produces an HTML report. The key goes only to the app's server route, and the bundled example run is clearly labelled illustrative placeholder data rather than real Jev output.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Is this email spam? | — |
| Choice | Which category? | marketing · finance · sales · customer support · other |
| Score | How urgent is it? | — |
How it works
- Pick or write an email, or sample the dataset
- Send one Jev request with three typed questions
- Show answers, probabilities and the raw request and response
- Compute spam accuracy against dataset labels
Strengths
- All three primitives in one call
- Request and response inspector for learning
- Example view works without a key
Caveats
- Bundled example data is placeholder, not real Jev output
- Demo only
Getting started
`npm install && npm run dev`, then add a TypeSafe key in Settings or TYPESAFE_API_KEY in .env.local.At a glance
- Type
- App
- Status
- prototype
- Language
- TypeScript
- Runtime
- Next.js app and Python script
- Has code
- yes
Use cases and integrations
How curated lists describe it
Showcase of TypeSafe JEV classifying emails: spam (noul), category (choice) and urgency (score) - Next.js + MUI app and Python script
logicrw/awesome-jev-projectsShowcase of TypeSafe JEV classifying emails: spam (noul), category (choice) and…
wh000wh000/awesome-jev-live
Frequently asked questions
What does Jev decide?
Spam probability, category and urgency for each email.
Can I try it without a key?
The example tab works without one, but its data is illustrative placeholder content.
Which dataset is used?
The public Enron-Spam test split.
Related projects
Google Apps Script that labels, archives or trashes Gmail conversations based on Jev answers to your plain-English yes/no questions.
ProjectbetaJavaScriptChrome/Brave extension that uses Jev to classify, label and safely bulk-clean a Gmail inbox with undo.
PluginbetaJavaScriptDry-run-first Proton Mail Bridge triage on macOS where Jev answers whether each message is spam or phishing.
ProjectbetaPythonGoogle Apps Script Gmail classifier that applies your own plain-English labels with Jev and archives only high-confidence unwanted mail.
ServicebetaJavaScriptRead-only Chrome extension that badges each Gmail message with Jev's category, priority, spam % and reply %.
Browser extensionprototypeJavaScriptCreator inbox sorter: Jev answers five questions per comment or DM and code decides to notify, draft, like, hide, archive or escalate.
ProjectprototypeTypeScript