Jev: Ask

Description

This is the most general node of the Jev family. It sends a text (state) and a set of typed questions to Jev, TypeSafe’s decision model, and returns one answer per question with probabilities. It does not generate text: it chooses among the options you define.

Jev evaluates all questions in a request in parallel, so adding questions barely increases latency. This is the fan-out pattern: ask everything that may be needed at once and decide later, in the workflow, which answers to use.

Question types

Type	Question it answers	`criteria`	Answer
`noul`	Is it true?	optional `{"true": "...", "false": "..."}`	probability from 0 to 1
`choice`	Which of these options?	options object (1 to 255)	option, confidence and probabilities
`score`	Which level of this scale?	levels list (1 to 10)	decimal score, confidence and probabilities

Configuration

Parameters

Parameter	Type	Required	Description
credentials_id	credentials	Yes	TypeSafe credential (API key).
model	select	Yes	Jev model. `jev-latest` is an alias that moves to new models on release (today `jev-1.13.0`); in production pin `jev-1.13.0` or `jev-1.14.0`.
state_mode	select	Yes	What is evaluated: `text` (a text), `object` (object with named fields, recommended) or `all` (all data reaching the node).
state	textarea	No	Text or JSON object to evaluate. Supports `\{\{field\}\}` variables.
long_context	boolean	No	Long context (experimental): raises the text limit from 64k to 262k tokens. It is slower and less accurate; use it only when the text does not fit otherwise.
output_key	text	No	Key in the data where the result is stored. Default `jev`; the rest of the data is kept.
questions	json	Yes	Map `{name: {type, instructions, criteria}}` or list `[{name, ...}]`. Names allow letters, digits, `_` and `-`.

Credentials

Requires a TypeSafe credential (credentials_id) holding the api_key from the TypeSafe console (TYPESAFE_API_KEY). The key is yours: TypeSafe bills the usage, not Floogos. In the credential, the Test button calls GET /v1/models (no tokens spent).

Output

The result is added to the input data (it does not replace it): the ticket or form stays available downstream. Read it as \{\{jev.field\}\}.

{
  "nextModule": "next-node",
  "data": {
    "...": "input data, untouched",
    "jev": {
      "answers": {
        "urgente": {
          "type": "noul",
          "probability": 0.95,
          "confidence": 0.9,
          "answer": "yes"
        },
        "equipo": {
          "type": "choice",
          "choice": "technical",
          "confidence": 0.7,
          "probabilities": {
            "billing": 0.1,
            "technical": 0.8,
            "sales": 0.1
          }
        },
        "enfado": {
          "type": "score",
          "score": 1.5,
          "normalized": 0.75,
          "label": "Very angry, strong language",
          "confidence": 0.6
        }
      },
      "model": "jev-1.13.0",
      "usage": {
        "input_tokens": 120,
        "output_tokens": 12
      },
      "cost_usd": 0.000005
    }
  }
}

A single output (nextModule).

Example

Triaging a ticket in a single call

Questions:

{
  "urgent": { "type": "noul", "instructions": "The message conveys urgency or time-sensitivity" },
  "team": {
    "type": "choice",
    "instructions": "Which team should handle this",
    "criteria": { "billing": "Payment or subscription issues", "technical": "Bugs or integration problems", "sales": "Pricing or account questions" }
  },
  "frustration": {
    "type": "score",
    "instructions": "How frustrated the customer appears",
    "criteria": ["Calm, just stating facts", "Frustrated but civil", "Very angry, strong language"]
  }
}

Notes

Privacy: the text you evaluate leaves Floogos for TypeSafe, a third party. Per their documentation it is not used for training, and zero retention exists only on their Enterprise plan. Do not send data you cannot share; filter first with the Jev: Verify rules node (pii) if needed.
Language: Jev performs best in English; other languages, Spanish included, work with lower accuracy. Test with your own data before automating, and write instructions in English if results are unreliable.
Variables: the engine substitutes \{\{field\}\} in the configuration before running the node. The node does not substitute again, so user text containing braces travels as-is.
Cost: 0.042 $ per million input tokens; output is free. jev.cost_usd is a per-run estimate.
Errors: missing_credentials, validation (configuration or 422), auth_error (401), rate_limited (429), overloaded (529), state_too_large, jev_error and connection_error. 429, 529, 5xx and network drops retry automatically (up to 3 times with growing delay); the rest do not.
Confidence: confidence is not an accuracy guarantee: calibrate thresholds with your own cases and start conservative. Do not automate destructive actions.