Jev & Laya API. Your preferred way to call it.

Sign in, create a JevTypeSafe key, and send the same judgment from your application, terminal or Agent. All entry points share your account credits across Jev and Laya models.

HTTP API

POST https://jevtypesafe.net/api/v1/decisions with your key in the Authorization header. Set JEVTYPESAFE_API_KEY in your secret environment.

curl https://jevtypesafe.net/api/v1/decisions \
  -H "Authorization: Bearer $JEVTYPESAFE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jev",
    "state": "Since yesterday, every CSV export from our dashboard has stopped halfway through...",
    "questions": {
      "routing": {
        "instructions": "Which team should handle this support ticket?",
        "type": "choice",
        "criteria": {
          "Billing": "Invoices, payments, subscriptions, or refunds.",
          "Technical": "Errors or product features that are not working.",
          "Account": "Login, access, or account settings."
        }
      }
    }
  }'

model selects between jev, laya-english, and laya-multilingual. state accepts text or JSON. questions maps your question IDs to definitions. A single request can answer up to 16 questions about the same input.

• choice: instructions plus a criteria object mapping answer labels to descriptions.
• noul: a Yes/No question. The returned probability is for Yes, from 0 to 1.
• score: an ordered criteria array of 2–10 descriptions. The result is a weighted zero-based score.

CLI

Run judgments directly from your command line terminal:

npx jevtypesafe decide --model laya-english --request request.json

Local MCP

Configure your Agent client to start jevtypesafe mcp over stdio. Pass your key through the client's secret environment.

Remote MCP, CLI installation, skill and connection management →