Jev directory
CommunityJev Integrations & Adapters
TypeSafe AI n8n Community Node
n8n community node that sends a state and typed questions to TypeSafe AI System One models, including Jev. Evaluate adds answers to each item; Route sends each item to an output based on one answer.
- Reading time
- 2 min
- Published by
- Community
- Added
- Oct 2026
Highlights
- Two operations: Evaluate adds answers to each item, Route picks an output per item.
- Supports Choice, Score, and Noul (yes/no) question types, each returning confidence or probability.
- State Format can be Text, JSON, or the incoming item's JSON.
- Route can add a Fallback output when an answer's confidence is below a set threshold.
- Installed from n8n community nodes using the package name @typesafe-ai/n8n-nodes-typesafe-ai.
Questions about this entry
Short answers drawn from the linked project or page.
Install it as a community node following the n8n community nodes installation guide, using the package name @typesafe-ai/n8n-nodes-typesafe-ai. Once installed, the node appears in your n8n workflow editor alongside other nodes.
You create an API key in the TypeSafe console, then add a TypeSafe AI API credential in n8n and paste the key into the API Key field. n8n checks the key when you save the credential.
Evaluate asks one or more questions about the state and adds all the answers to the item. Route asks one question and sends the item to the output that matches the answer, such as one output per choice route.
Three types are supported. Choice returns the option picked from your list plus its confidence. Score returns a position along your levels plus its confidence. Noul (yes/no) returns the probability that the answer is yes, from 0 to 1.
For Choice questions, set Confidence Handling to Route to Separate Fallback Output to add a Fallback output for answers below the confidence threshold. For Noul, both thresholds start at 0.5; setting them apart, for example 0.8 and 0.2, adds an Uncertain output.
Yes, as a preview feature. Images adds PNG or JPEG images from the item's binary data; you give each image a Reference and write that reference in the state, a question's instructions, or its criteria. Each image must be 280 to 1568 pixels on each side.
Yes. Set Questions Format to Using Raw JSON and pass a JSON object of questions in the API's format, such as one built by an earlier node. The API reference documents that format.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Facebook: Intake Router keeps diagnosis out of the answer space at the front desk.
FacebookClinicnotes
X: OpenRouter Decision Model Rankings
X: herdr + jev, an agent router
X: A group chat bot with decision room routing
More Jev resources like this
LangChain.js integration for TypeSafe System One models. It wraps the jev classifier as a Runnable that returns typed choice, score, and noul answers with calibrated probabilities, plus agent middleware for model routing and tool gating.
Jev Integrations & Adapters#typescript#sdk#routing
Community
TypeScript service and library that places Jev between a PBX such as Asterisk or FreePBX and call destinations, classifying caller intent into predefined routes. Each route maps to an explicit PBX action, with low-confidence or unhandled calls sent to a fallback route.
Jev Integrations & Adapters#typescript#routing#github
Communityrayanweragala/jev-call-router
First-party TypeSafe AI decision provider for Standard Agents. It implements DecisionProviderInterface with kind 'decision' and decide(), sending explicit context and multiple independent questions to Jev in one request.
Jev Integrations & Adapters#typescript#sdk#agents
Community
TypeSafe Jev adapter for TanStack AI. It exposes typed evaluate decisions over HTTP, letting TanStack AI applications route requests through Jev's System One model from JavaScript or TypeScript.
Jev Integrations & Adapters#typescript#javascript#sdk
Community
Optional TypeSafe AI Jev decision provider for the Zhin chat framework. Evaluates named Choice, Score and Noul questions through a plugin-managed client, returning labels, distributions and confidence without generating chat replies or granting tool permissions.
Jev Integrations & Adapters#typescript#sdk#routing
Community
TypeScript package that implements the IDecisionModel interface for @mcp-abap-adt/llm-agent on top of @typesafe-ai/sdk, letting an agent ask Jev typed yes/no, choice, and score questions about a state and get numbers back.
Jev Integrations & Adapters#typescript#sdk#agents
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.