Jev: Yes/No condition

Description

An If with judgement: instead of comparing a field to a value, it asks Jev something that can only be decided by reading the text (“is the customer asking for a refund?”, “does the message convey urgency?”) and exits through one of three outputs:

Yes: probability is equal to or above the Yes threshold (default 0.7).
No: equal to or below the No threshold (default 0.3).
Uncertain: in between. This is the output for human review.

If Uncertain is not connected, the flow follows the likelier side and the node behaves like a normal yes/no (jev.route_fallback will be true).

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.
question	textarea	Yes	Yes/no statement Jev must answer, e.g. “The message conveys urgency”.
criteria_true	textarea	No	When it counts as “Yes” (optional).
criteria_false	textarea	No	When it counts as “No” (optional).
threshold_yes	number	No	Yes if probability is at or above. Default 0.7.
threshold_no	number	No	No if probability is at or below. Default 0.3. Must be lower than the Yes 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": {
      "answer": "yes",
      "probability": 0.93,
      "confidence": 0.86,
      "route": "yes",
      "route_fallback": false,
      "model": "jev-1.13.0",
      "usage": {
        "input_tokens": 80,
        "output_tokens": 3
      },
      "cost_usd": 0.000003
    }
  }
}

Several outputs: route_yes, route_no, route_uncertain. Each port connects to its target; the node chooses which one to exit through.

Example

Escalate only what is urgent

State: \{\{message\}\}. Question: The customer is asking for a refund. Connect Yes to the node that creates the refund task, No to the normal flow and Uncertain to a notification for a person.

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.