n8n-nodes-jev-classification
n8n Jev Classification node that branches items by category with a Needs Review branch, plus parallel and batched requests.
Overview
n8n-nodes-jev-classification wraps Jev as a Jev Classification node that behaves like n8n's built-in Text Classifier: one output branch per category plus a Needs Review branch for low-confidence items. It also supports scoring and yes/no checks, and is built for volume with parallel requests and packing many items into a single request.
The README contrasts it with an LLM plus structured output parser: Jev's answers are always one of your categories, carry calibrated probabilities you can threshold, and cost input tokens only, citing TypeSafe's documentation for price and batching savings. A tool variant lets AI Agents call it when the instance allows community tools. It is for n8n users who classify large volumes of tickets, reviews or records.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which category does this text belong to? | — |
| Score | Score this text on an ordered scale | — |
| Yes / no | Does this text meet the check? | yes · no |
How it works
- Install the node and add a TypeSafe credential.
- Define categories and a confidence threshold.
- Items are sent in parallel or packed into batched requests.
- Each item exits on its category branch or Needs Review.
Strengths
- Familiar Text Classifier-style branching.
- Batching many items per request for cost and speed.
- Built-in low-confidence review path.
Caveats
- Requires a TypeSafe key; cost and speed figures are TypeSafe's own.
- Agent tool variant needs an instance setting enabled.
Getting started
In n8n: Settings > Community Nodes > Install n8n-nodes-jev-classification (or npm i n8n-nodes-jev-classification in ~/.n8n/nodes) and restart.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
N8n community node for Jev by TypeSafe AI: classify, score and check text with calibrated probabilities. Parallel requests and multi-item batching.
hellogumbo/awesome-jev
Frequently asked questions
How is it different from n8n's Text Classifier?
It uses Jev's calibrated probabilities and adds a Needs Review branch for uncertain items.
Can it process many items cheaply?
Yes, it runs requests in parallel and can pack multiple items into one request.
Can AI agents use it?
A tool variant appears when the instance enables community node tool usage.
Related projects
Workflow DSL for existing agents that uses Jev for the steps that are decisions and calls an agent only when investigation is needed.
LibrarybetaTypeScriptOpen-source workspace for building, deploying and monitoring AI agents and workflows, listed as integrating TypeSafe System One.
ProjectproductionTypeScriptn8n community node for Jev that adds a typed smart if-statement: choice, score and noul with probabilities in workflows.
ProjectbetaTypeScriptn8n node that sends a state and a map of typed questions to /v1/systemone in one request and returns per-question answers.
ProjectbetaTypeScriptn8n community node for TypeSafe's System One API with yes/no, choice and score questions, retry handling and an AI Agent tool.
ServicebetaTypeScriptPython library to batch, gate, trace and calibrate thousands of typed Jev decisions, maximising questions per call.
ProjectprototypePython