AgentRouter
Sign in
TypeSafeTypeSafe

Evaluate typed questions with Jev

/systemone

Use TypeSafe Jev to classify, score or verify text and JSON evidence. Batch named questions against the same state and receive a decision and probabilities for each.

Finished calls, last 7 days
0

Cancellations excluded. Execution times cover successful calls.

Use it with your agent

Set up https://www.agentrouter.to/SKILL.md, then use TypeSafe’s /systemone endpoint through AgentRouter.

Inputs

stateRequired
Text or structured JSON shared by every question.
questionsRequired
Name each question and give its instructions. Use noul for yes/no probability, choice for named options, or score for ordered levels.

Example input

{
  "state": {
    "ticket": "I see two charges for the same order. Please refund one."
  },
  "questions": {
    "duplicate": {
      "type": "noul",
      "instructions": "Does the customer report a duplicate charge?"
    },
    "team": {
      "type": "choice",
      "instructions": "Which team should handle this?",
      "criteria": {
        "billing": "Payments or refunds",
        "technical": "Product failures"
      }
    },
    "urgency": {
      "type": "score",
      "instructions": "Rate the urgency.",
      "criteria": [
        "Routine request",
        "Needs prompt attention",
        "Immediate outage"
      ]
    }
  }
}

Output

Resolved model and answers keyed by question ID. Noul returns the probability of yes. Choice and score include a probability distribution and confidence. Usage reports input and output tokens.