First-party app
Jev

Jev

Evaluate state against typed questions with TypeSafe's System One (Jev).

stable AI & Machine Learning

About

Jev ships in the w6w first-party pack. It declares 2 actions, 1 health check, and the host runs its code in a sandbox that never sees the credential.

App id
io.w6w.jev
Version
0.1.0
Author
w6w
Licence
MIT
Categories
AI & Machine Learning

Overview

Jev is TypeSafe’s System One evaluation API. A workflow hands it a description of some state plus a map of typed questions, and gets back one typed answer per question — a structured verdict rather than free-form chat.

The app lists the models available to the API key and runs evaluations against any of them, so the model choice stays explicit in the workflow.

A fit for classification, validation and decision steps where a downstream step needs a typed answer it can branch on.

Build with Jev

Three routes to the same 2 actions. The Workflow tab is generated from Jev's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.

Evaluate

evaluate

Answer a map of typed questions about a state with Jev System One.

List Models

list-models

List all Jev models available to this API key.

A workflow step names the app and the action, and the editor fills in the connection when you pick one. This is the Step shape from the workflow spec, carrying Jev's real ids.

{
  "manifestVersion": "2",
  "name": "jev-example",
  "steps": [
    {
      "id": "evaluate",
      "uses": {
        "app": "io.w6w.jev",
        "action": "evaluate",
        "connection": "conn_YOUR_CONNECTION_ID"
      },
      "with": {
        "model": "<model>",
        "state": "<state>",
        "questions": "<questions>"
      }
    }
  ]
}

Here are some of the things you can do

  • Evaluate

    perform
    evaluate
  • List Models

    read
    list-models

Every app-specific value here is a blank you have to fill in. An app action is reached through the connection that authenticates it, so the address is a connection id, not the app id — and connections belong to your account, so a public page cannot know yours. Create one for Jev, then fill in the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the parameters that action declares. The call itself is real — the shape is transcribed from the studio's own snippet builder, which prints the same kind of blanks — but nothing in it is specific to Jev. The Workflow tab is where this app's real ids are.

Install
npm install @w6w/sdk
yarn add @w6w/sdk
pnpm add @w6w/sdk
deno add npm:@w6w/sdk
Code
import { W6wClient, isActionRun } from "@w6w/sdk";

// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();

const envelope = await client.run({
  urn: "conn_YOUR_CONNECTION_ID",
  action: "evaluate",
  payload: {
    model: "<value>",
    state: "<value>",
    questions: "<value>",
  },
});

if (isActionRun(envelope)) console.log(envelope.value);
Install the CLI
npm install -g @w6w/cli
CLI
w6w run conn_YOUR_CONNECTION_ID --action evaluate --payload '{"model":"<value>","state":"<value>","questions":"<value>"}'

Give an AI agent Jev — without giving it Jev's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.

One tool call
{
  "name": "w6w_invoke",
  "arguments": {
    "ref": "app:io.w6w.jev#evaluate",
    "input": {
      "model": "<model>",
      "state": "<state>",
      "questions": "<questions>"
    }
  }
}

Every tool names its target with a single ref. The app: form above doesn't name a connection at all — the host resolves which of the caller's Jev connections to sign with, and refuses rather than guesses when the answer is ambiguous.

What the agent gets

Credentials it can't read

The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.

A tool surface scoped to the caller

Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.

A durable workflow in one call

Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.

Health-aware discovery

Jev's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.

The MCP surface is part of the hosted platform. Jev itself is MIT, and the runtime that executes it is source-available (FSL).

Request MCP access

Health checks

Jev declares its own checks, so its health is a property of the app rather than something the host guesses at.

service

Jev API reachability

Probes GET /models and reports the service down on 5xx responses.