n8n-nodes-typesafe-jev
Community n8n node for asking multiple typed questions over workflow state.
# n8n-nodes-typesafe-jev
An n8n community node for [TypeSafe Jev](https://typesafe.ai), the TypeSafe System One model for fast, structured decisions.
Jev returns typed decisions rather than generated prose. In a single node execution you can ask several independent questions about the same state and get back calibrated probabilities for classification, routing, verification and scoring.
> Unofficial and community-maintained. Not affiliated with, endorsed by, or supported by TypeSafe.
## Installation
In n8n, go to **Settings → Community Nodes**, select **Install**, and enter:
```text
n8n-nodes-typesafe-jev
```
## Credentials
Create an API key in the TypeSafe console, then add a **TypeSafe API** credential in n8n and paste the key. Press **Test** to confirm it works. The credential is checked against the model list endpoint.
| Field | Required | Notes |
| --- | --- | --- |
| API Key | yes | Stored encrypted by n8n and never written to output data |
| Base URL | no | Defaults to `https://api.typesafe.ai`. Change only for a proxy or dedicated deployment. |
## Node configuration
1. Pick a **Model**, or leave the default. The dropdown is loaded from your account.
2. Supply **State** as plain text, a JSON object or a JSON array. Defaults to the whole incoming item (`{{ $json }}`).
3. Choose **Question Builder** to define questions field by field, or **JSON** to supply a schema generated upstream.
4. Give every question a **Name**. That name is the key its answer appears under.
### Question types
| Type | You provide | Jev returns |
| --- | --- | --- |
| **Choice** | Two or more labelled options, each with an optional description | `choice`, `confidence`, and a probability per label |
| **Yes/No** | Optional descriptions of what counts as yes and no | `noul`, the p