Jev by TypeSafe

Jev by TypeSafe

Fast, cheap yes/no, classification and rating decisions for AI agents with Jev, TypeSafe's System One model: typed answers with calibrated probabilities in about 300 ms, instead of a paragraph to parse.

7 Tage gratis · keine Kreditkarte · EU-Hosting

Frag Jev alles

Teste einen echten Prompt gegen Jev by TypeSafe via AnythingMCP — Claude ruft die Tools auf, liefert die Antwort. Drück Enter auf deine eigene Nachricht, um auf Cloud zu installieren.

Jev auf Cloud installieren
Jev by TypeSafe · live via MCP
Teilen
Opus 4.7

Claude ist KI und kann Fehler machen. Bitte Antworten gegenprüfen.

Setup in 2 Minuten

  1. 1Free Trial auf cloud.anythingmcp.com starten.
  2. 2Im Connector-Store auf Jev by TypeSafe klicken. Credentials einfügen.
  3. 3MCP-API-Key generieren und KI-Client auf die MCP-URL zeigen.
Jev by TypeSafe jetzt installieren

Anleitungen für Jev

Schritt-für-Schritt-Setup für die wichtigsten KI-Clients.

Jev by TypeSafe einrichten

Direkt aus der Connector-Definition: wo du die Credentials findest, welche Rechte sie brauchen und mit welcher API dieser Adapter spricht. Vom Connector-Autor auf Englisch bereitgestellt.

Jev is a decision model, not a chat model. You give it state (the evidence) and one or more typed questions; it returns a number or an option with probabilities in about 300 ms. It never writes text. Use it when an agent needs a judgment it can branch on: is this urgent, which team owns it, how risky is it, does this reply answer the question, is this record a duplicate.

Start with jev_playbook. It costs no API call and explains how to phrase questions, what to put in state and how to read the probabilities.

Setup: create an API key at https://console.typesafe.ai and paste it into TYPESAFE_API_KEY. Jev is billed per input token (about $0.04 per million), output is free.

Tools

  • jev_yes_no: one yes/no question, returns the probability that the answer is yes.
  • jev_classify: pick one option from a set you define, with a probability per option and a confidence.
  • jev_rate: place the state on ordered levels (2 to 10), returns a 0-indexed score, the level probabilities and a legend.
  • jev_ask: the full API: several questions of any type over the same state in one call (they run in parallel and cost the same state tokens once).
  • jev_list_models: model names your key can use.

Question types (the API calls a yes/no question noul, never bool): noul (probability 0 to 1), choice (one option, max 255), score (ordered levels, max 10).

Reading answers: a yes/no value near 0.5 means unsure, not medium. confidence on choice and score measures how concentrated the probabilities are, not whether the answer is right. A score over N levels runs from 0 to N-1: 2.6 on 4 levels sits between level 2 and 3. Decide thresholds in your own logic: act on confident answers, re-ask or escalate to the user when it is unsure.

Limits: text only (no images), 32k tokens for state plus the longest question, 64k per request. English is the strongest language; German, Italian and others work but check confidence.

Deine KI ist zwei Klicks von Jev by TypeSafe entfernt.

Connector installieren, Credentials einfügen, KI fragen. 7 Tage gratis, keine Kreditkarte.