Jev: Score

Description

Scores a text on one or several dimensions; each is a scale of 2 to 10 described levels (“Calm”, “Frustrated”, “Very angry”…). Jev evaluates all of them in parallel and independently.

Scores are normalized to 0-1 and combined with weights defined here, in the node (visible and adjustable):

composite = Σ weight × (normalized level) ÷ Σ weights

With a single dimension it is a simple score. The node routes to Low (composite below the low threshold, 0.34 by default), High (at or above the high threshold, 0.67) or Medium.

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.
dimensions	json	Yes	List `[{name, instructions, criteria: [levels], weight}]`. `weight` defaults to 1 and must be greater than 0.
threshold_low	number	No	Below this value: Low. Default 0.34.
threshold_high	number	No	From this value: High. Default 0.67. Must be greater than the low one.

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": "selected-route-target",
  "data": {
    "...": "input data, untouched",
    "jev": {
      "composite": 0.6,
      "band": "mid",
      "route": "mid",
      "route_fallback": false,
      "dimensions": {
        "encaje": {
          "score": 3,
          "normalized": 1,
          "label": "Excellent fit",
          "confidence": 0.8,
          "weight": 0.5
        },
        "urgencia": {
          "score": 0,
          "normalized": 0,
          "label": "No timeline",
          "confidence": 0.7,
          "weight": 0.3
        },
        "presupuesto": {
          "score": 1,
          "normalized": 0.5,
          "label": "Mentioned vaguely",
          "confidence": 0.6,
          "weight": 0.2
        }
      },
      "model": "jev-1.13.0",
      "usage": {
        "input_tokens": 200,
        "output_tokens": 9
      },
      "cost_usd": 0.000008
    }
  }
}

Several outputs: route_low, route_mid, route_high. Each port connects to its target; the node chooses which one to exit through.

Example

Lead qualification

Dimensions fit (0.5), urgency (0.3) and budget (0.2). High creates the deal in the CRM and alerts sales; Medium adds it to a follow-up sequence; Low archives it.

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.