TypeSafe-compatible typed questions | milliseconds.ai documentation

curl -X POST https://api.milliseconds.ai/v1/systemone \
     -H "Authorization: Bearer <token>" \
     -H "Content-Type: application/json" \
     -d '{
  "state": "Shoes arrived two weeks late and in the wrong size. Also I see two charges on my card. What are you going to do about this?",
  "questions": {
    "department": {
      "criteria": {
        "billing": "Charges, invoices, payment problems",
        "returns": "Exchanges, refunds, wrong or damaged items",
        "shipping": "Delivery status, delays, lost packages"
      },
      "instructions": "Which team should handle this?",
      "type": "choice"
    },
    "double_charge": {
      "criteria": {
        "false": "No duplicate charge is mentioned",
        "true": "The customer says they were charged more than once"
      },
      "instructions": "Does the customer report a duplicate charge?",
      "type": "noul"
    },
    "urgency": {
      "criteria": [
        "can wait",
        "this week",
        "today"
      ],
      "instructions": "How urgent is this ticket?",
      "type": "score"
    }
  },
  "model": "decision-machine-1"
}'

{
  "model": "decision-machine-1",
  "answers": {
    "department": {
      "choice": "billing",
      "confidence": 0.438,
      "probabilities": {
        "billing": 0.625,
        "returns": 0.242,
        "shipping": 0.133
      },
      "type": "choice"
    },
    "double_charge": {
      "noul": 0.592,
      "type": "noul"
    },
    "urgency": {
      "confidence": 0.658,
      "legend": {
        "0": "can wait",
        "1": "this week",
        "2": "today"
      },
      "probabilities": {
        "0": 0.602,
        "1": 0.112,
        "2": 0.286
      },
      "score": 0.684,
      "type": "score"
    }
  },
  "usage": {
    "input_tokens": 394,
    "output_tokens": 0
  }
}

Drop-in for TypeSafe’s POST /v1/systemone with model: "decision-machine-1". One state (string, object or array), a map of named questions of type noul, choice or score, and one typed answer per question with the model’s own probabilities. Each question runs as the matching capability (yes-no, classify, rate) on the same text and counts as one request against the rate limit. No image input on this route.

Authentication

AuthorizationBearer

A milliseconds API key, test_sk-{namespace}-{entropy} or prod_sk-{namespace}-{entropy}. Every /v1 route requires it.

Request

This endpoint expects an object.

statestring or double or boolean or map from strings to any or list of anyRequired

A string, or an object or array rendered to text.

questionsmap from strings to objectsRequired

modelstringOptional

Response

One answer per question

modelstring

answersmap from strings to objects

usageobject

Errors

400

Bad Request Error

404

Not Found Error