---
title: "Jev"
description: "Jev is TypeSafe's model for making structured decisions from text. You send state and typed questions, and Jev returns values your code can use directly."
url: https://exe-staging.dev/deploy/jev
category: "AI agents"
updated: 2026-10-17
---

# Jev

Call TypeSafe's decision model through an HTTP integration

- **Software:** Jev (https://typesafe.ai)
- **Example VM name:** `my-jev` (yours will differ; on the VM, `hostname` prints it)
- **Machine-readable:** https://exe-staging.dev/deploy/jev/manifest.json

## What you get

- The `typesafe` HTTP proxy integration attached to your VM, so the API key stays outside it
- A Jev call from the VM through `https://typesafe.int.exe.xyz`
- An `answers.is_urgent.noul` value between `0` and `1` from the example request

Running on the VM:

- **typesafe integration**: An exe.dev [HTTP proxy integration](/docs/integrations-http-proxy) to `https://api.typesafe.ai`

How it is reached:

- https://typesafe.int.exe.xyz/ (private): Jev, from the attached VM, with the bearer token added for you

## Deploy with Shelley

Open https://exe-staging.dev/new?prompt=Set%20up%20Jev%20on%20this%20VM%20by%20following%20the%20exe.dev%20recipe%20at%20https%3A%2F%2Fexe-staging.dev%2Fdeploy%2Fjev.md%20from%20top%20to%20bottom.%0A%0AThe%20recipe%27s%20example%20VM%20name%20is%20my-jev.%20This%20VM%27s%20name%20is%20the%20output%20of%20%60hostname%60%3A%20use%20it%20wherever%20the%20recipe%20writes%20my-jev.%20Skip%20the%20step%20that%20creates%20the%20VM%3B%20you%20are%20on%20it.%0A%0AYou%20are%20done%20when%20all%20of%20these%20are%20true.%20Check%20each%20one%20yourself%3A%0A-%20The%20%60typesafe%60%20HTTP%20proxy%20integration%20attached%20to%20your%20VM%2C%20so%20the%20API%20key%20stays%20outside%20it%0A-%20A%20Jev%20call%20from%20the%20VM%20through%20%60https%3A%2F%2Ftypesafe.int.exe.xyz%60%0A-%20An%20%60answers.is_urgent.noul%60%20value%20between%20%600%60%20and%20%601%60%20from%20the%20example%20request%0A%0AOnly%20I%20can%20create%20the%20integration%2C%20from%20my%20own%20computer%2C%20and%20the%20API%20key%0Amust%20never%20be%20on%20this%20VM.%20Give%20me%20the%20%60integrations%20add%60%20command%20first%2C%0Awith%20this%20VM%27s%20name%20in%20it%2C%20and%20wait%20until%20I%20say%20I%27ve%20run%20it.%20Then%20make%0Athe%20example%20call.%0A%0AFinish%20with%20the%20URLs%20I%20should%20open.%0A to create a VM whose agent, Shelley, follows this recipe. From a terminal:

```sh
curl -fsSL https://exe-staging.dev/deploy/jev/prompt.txt | ssh exe.dev new --prompt=/dev/stdin
```

Or follow the steps below by hand.

[Jev](https://docs.typesafe.ai/introduction) is TypeSafe's model for making
structured decisions from text. You send state and typed questions, and Jev
returns values your code can use directly.

Create an [HTTP proxy integration](/docs/integrations-http-proxy) so the API
key stays outside your VM. Get a key from the
[TypeSafe dashboard](https://console.typesafe.ai/keys), export it in your local
shell, and attach the integration to your VM:

```bash
printf '%s' "$TYPESAFE_API_KEY" | \
  ssh exe.dev integrations add http-proxy \
    --name typesafe \
    --target https://api.typesafe.ai \
    --bearer=- \
    --attach vm:my-jev
```

From the attached VM, call the integration hostname instead of
`api.typesafe.ai`. The proxy adds the bearer token before forwarding the
request:

```bash
curl --fail-with-body https://typesafe.int.exe.xyz/v1/systemone \
  --json '{
    "state": "My payout has been delayed for three days. Please help ASAP.",
    "model": "jev-latest",
    "questions": {
      "is_urgent": {
        "type": "noul",
        "instructions": "Does this message express urgency?"
      }
    }
  }'
```

The response contains an `answers.is_urgent.noul` value between `0` and `1`.
See TypeSafe's [API reference](https://docs.typesafe.ai/api) for Choice, Score,
and Noul questions.

## Related

- [Run Claude Code on a remote server](https://exe-staging.dev/deploy/claude-code.md): A computer for Claude. A breather for your laptop.
- [Host OpenClaw](https://exe-staging.dev/deploy/openclaw.md): An AI sidekick with its own computer. Your laptop can take a nap.
- [Self-host Hermes Agent](https://exe-staging.dev/deploy/hermes-agent.md): An agent that remembers you, on a computer that never sleeps.
- [Host a Pi Durable agent](https://exe-staging.dev/deploy/pi-durable.md): An agent that picks up where it left off, even after kill -9.
- [Running Agents](https://exe-staging.dev/deploy/agents.md): Use exe.dev VMs as a sandbox
- [Flue](https://exe-staging.dev/deploy/flue.md): Run Flue agentic apps on exe.dev