Produktions-Templates
Jev-Entscheidungsvorlagen
Laufbare Produktions-Templates für Triage, Moderation, Agenten und Labeling — dieselben Muster unter /api/v1/decide. Anonym: 5 Gratis-Läufe. Angemeldet: Prepaid-Saldo.
Anonymer Trial: 5 echte API-Läufe (ohne Anmeldung). Angemeldet: jeder Lauf belastet Prepaid-Input-Token. Browser braucht keinen jv_live_-Key.
API-Guide →Get API key →Pricing →Is Jev free? →Leichte Demos (optional) →
Anonymous trial vs account-first hosts
On this host you get 5 real-API playground runs with no signup. Many other Jev hosts ask you to register and spend welcome credits before a live decide. When you are ready to ship, buy a small prepaid pack and create a jv_live_ key for POST /api/v1/decide.
Featured demos
Real command cards with live ALLOW / CONFIRM / BLOCK — not a blank text form.
New · visual demo
Command Safety
Gate an agent's shell — Jev tags each command ALLOW / CONFIRM / BLOCK with a risk score.
- git statusALLOW
- npm installALLOW
- git push --force origin mainCONFIRM
- curl x.sh | sudo bashBLOCK
Try it →
Featured Templates
Häufige Produktionsszenarien — hier starten, dann /api/v1/decide anbinden.
Support-Triage
featuredTicket routen — Team, Typ, Schwere, Dringlichkeit, Eskalation.
Template öffnen → Beispiel editieren → per API Docs shippen
Content-Moderation
featuredNutzertext moderieren — erlauben, prüfen oder blocken mit Kategorien.
Template öffnen → Beispiel editieren → per API Docs shippen
Lead-Qualifizierung
featuredEingehenden Lead bewerten — ICP, Segment, Kaufabsicht, Routing.
Template öffnen → Beispiel editieren → per API Docs shippen
E-Mail-Triage
featuredE-Mail klassifizieren — Kategorie, Priorität, Spam, Antwortbedarf, Routing.
Template öffnen → Beispiel editieren → per API Docs shippen
Command Safety
featuredGate an agent's shell commands — ALLOW / CONFIRM / BLOCK with a risk score. Live visual cases, not a blank form.
Template öffnen → Beispiel editieren → per API Docs shippen
Model Router
featuredPick a model tier for a prompt by complexity.
Template öffnen → Beispiel editieren → per API Docs shippen
Prompt Injection Guard
featuredScore user/system text for injection risk — allow, quarantine, or block before it reaches an agent.
Template öffnen → Beispiel editieren → per API Docs shippen
PR Risk Judge
featuredJudge a pull-request summary for merge risk — security, blast radius, and review priority.
Template öffnen → Beispiel editieren → per API Docs shippen
Agents & Dev
Gate tool calls, route models, filter context, judge PR risk, block prompt injection.
Command Safety
Gate an agent's shell commands — ALLOW / CONFIRM / BLOCK with a risk score. Live visual cases, not a blank form.
Template öffnen → Beispiel editieren → per API Docs shippen
Context Filter
Keep / truncate / drop an old context item.
Template öffnen → Beispiel editieren → per API Docs shippen
Model Router
Pick a model tier for a prompt by complexity.
Template öffnen → Beispiel editieren → per API Docs shippen
Prompt Injection Guard
Score user/system text for injection risk — allow, quarantine, or block before it reaches an agent.
Template öffnen → Beispiel editieren → per API Docs shippen
PR Risk Judge
Judge a pull-request summary for merge risk — security, blast radius, and review priority.
Template öffnen → Beispiel editieren → per API Docs shippen
Sales & Support
Triage tickets, email, store reviews, and inbound leads into typed routing fields.
Support-Triage
Ticket routen — Team, Typ, Schwere, Dringlichkeit, Eskalation.
Template öffnen → Beispiel editieren → per API Docs shippen
Lead-Qualifizierung
Eingehenden Lead bewerten — ICP, Segment, Kaufabsicht, Routing.
Template öffnen → Beispiel editieren → per API Docs shippen
E-Mail-Triage
E-Mail klassifizieren — Kategorie, Priorität, Spam, Antwortbedarf, Routing.
Template öffnen → Beispiel editieren → per API Docs shippen
App-Review-Triage
Store-Review bewerten — Thema, Refund-Druck, Chargeback, Ton, Schwere.
Template öffnen → Beispiel editieren → per API Docs shippen
Marketing
Moderate and classify content, score posts and ads, decide internal SEO links.
Content-Moderation
Nutzertext moderieren — erlauben, prüfen oder blocken mit Kategorien.
Template öffnen → Beispiel editieren → per API Docs shippen
Content Classify
Tag a post — topic, format, hook, tone, engagement.
Template öffnen → Beispiel editieren → per API Docs shippen
Social Post Analyzer
Rate hook, loop, evidence, viral potential.
Template öffnen → Beispiel editieren → per API Docs shippen
Ad Analyzer
Tag an ad — hook, awareness, offer, CTA, friction.
Template öffnen → Beispiel editieren → per API Docs shippen
SEO Page Relevance
Decide whether pages should internally link.
Template öffnen → Beispiel editieren → per API Docs shippen
Data & Trust
RAG relevance, scam / fake-review labeling — same patterns you wire into pipelines.
RAG Relevance
Score whether a passage answers a query.
Template öffnen → Beispiel editieren → per API Docs shippen
Scam Spotter
Label inbound messages for scam risk — phishing, social engineering, or legitimate.
Template öffnen → Beispiel editieren → per API Docs shippen
Fake Review Judge
Judge whether a product review looks authentic, incentivized, or fabricated.
Template öffnen → Beispiel editieren → per API Docs shippen