n8n-nodes-jev
Helper n8n node for Jev by Brains of Bots: classify, route and score with a probability per answer to send unsure items to review.
Overview
This n8n community node, maintained by Brains of Bots and not by TypeSafe, adds Jev to workflow judgment steps such as which team should handle a ticket, whether a lead is a good fit, or whether a message contains personal data. You define the question and allowed answers; Jev returns one of them with a probability for each option, so there is no JSON to parse.
The README compares this with the usual LLM node plus Structured Output Parser plus IF node pattern, noting that Jev always returns a defined option, answers all questions in a request in parallel, and charges for input tokens only per TypeSafe's pricing. It covers question types, use cases, credentials, example workflows, how to write good questions, and limits and costs. CI and an npm package are provided.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which team should handle this ticket? | — |
| Yes / no | Does this message contain personal data? | yes · no |
| Score | How good a fit is this lead? | — |
How it works
- Install the node and add TypeSafe credentials.
- Define questions and allowed answers.
- Jev returns an option with per-option probabilities.
- Route low-probability items to a person.
Strengths
- Replaces LLM-plus-parser-plus-IF chains with one node.
- Probabilities make uncertainty visible.
- Guidance on writing good questions.
Caveats
- Third-party helper; not supported by TypeSafe.
- Requires a TypeSafe API key.
Getting started
Install n8n-nodes-jev from Community Nodes in self-hosted n8n and add a TypeSafe credential.At a glance
- Type
- Project
- Status
- beta
- Language
- TypeScript
- Runtime
- n8n community node
- Has code
- yes
- Has tests
- yes
Use cases and integrations
How curated lists describe it
Helper n8n community node for Jev by TypeSafe. Classify, route, and score text with questions you define, and get a probability for every answer so unsure items can go to review.
hellogumbo/awesome-jev
Frequently asked questions
Who maintains it?
Brains of Bots; it is not made or supported by TypeSafe.
Why not just use an LLM node?
Jev always returns one of your defined answers with probabilities, so no parsing or format checks are needed.
Where do I report problems?
Node issues go to the repository; account and model questions go to TypeSafe.
Related projects
Scaffold of n8n workflow patterns using Jev for PII screening, agent guardrails as hooks, and workflow evals with Jev as judge.
ProjectprototypeVercel Labs example routing form submissions to the right team with Jev via AI SDK, falling back to an LLM when uncertain.
LibraryprototypeTypeScriptAx, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.
PluginproductionTypeScriptCline's official curated plugin collection, which includes jev-browser, jev-guard and jev-playground plugins.
PluginproductionTypeScriptComposio agent SDK with an optional TypeSafe provider that uses Jev to shortlist and pick tools and closed-set arguments.
ProjectproductionTypeScriptEffect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.
ProjectproductionTypeScript