TypeSafe AI Jev tutorial · updated September 28, 2026

TypeSafe AI: How to Use Jev

TypeSafe AI develops Jev for decisions inside software. Learn how to use its model on the independent Jev AI playground: start with a support ticket, ask typed questions, read the probabilities and reuse the request in your app.

Open the Jev playground Jump to the API

This is an independent TypeSafe AI Jev guide. Read the Jev model overview for capabilities and limits.

Support ticketRECORDED EXAMPLE

“Our payouts have failed every day since Monday… If this is not fixed today we will have to move to another provider.”

TextJevDecisions

Route to billingUrgent 96%

Excerpt from the example below · 2026-09-18
Model probability, not a measured accuracy rate.

TypeSafe AI: choose where to use Jev

TypeSafe AI and Jev AI provide separate services. The model developer, the SDK publisher and the service receiving your request are not interchangeable.

You want to	Where to start	Account and usage
Use TypeSafe AI directly	TypeSafe AI website · official console · official docs	Use a TypeSafe AI account and the official service's keys and billing.
Follow this playground tutorial	Jev AI playground · API keys	Use your account and balance on this independent platform. See current plans.

The steps below use Jev AI. A purchase here does not add balance to TypeSafe AI. You can inspect all recorded examples before signing in; live runs use your available balance.

Try TypeSafe AI's Jev with a real case

Use an example to learn the controls, then replace the text with your own.

Open the playground and select Support ticket triage.
Keep a Jev model selected. The API alias for the current default is jev-latest.
Read the Text field and the questions beneath it. Select Your own case when you want to start blank.
Paste the text Jev should judge. Include the relevant context, such as the message and the routing rules.

The playground allows up to 8,000 characters and 8 questions per request. API limits differ; see the API reference.

Text / stateSUPPORT TRIAGE

Hi, this is the third time I am writing. Our payouts have failed every day since Monday and my team cannot pay suppliers. I already re-entered the bank details twice. If this is not fixed today we will have to move to another provider.

This is the shared input for all four questions in the example.

Write questions for TypeSafe AI's decision model

Switch between three questions about the same ticket. The output shown is a saved recording, not a live call.

YOUR QUESTION

Which team should handle this ticket?

Define distinct options and describe what each one means. Read the chosen label and the full probability distribution.

billingPayments, payouts, invoices and refunds
technicalBugs, outages, integrations and API errors
salesPricing, upgrades and new accounts
accountLogin, profile and permissions

RECORDED JEV ANSWER · 2026-09-18

Choice100% sure

Which team should handle this ticket?

billing

billing 100%
technical 0%
sales 0%
account 0%

answers.team.choicebilling

This interactive example only replays recorded data. It does not call the API or use your balance.

Run your text and interpret the result

Editing an example changes the request. Run it again to get an answer for the new input.

Click Sign in to run if you are signed out.
Review your text and questions, then click Run selected model.
Read the Answers panel. A fresh response is marked Live; the initial example is recorded output.
Check uncertain or unexpected decisions against your own examples before using them to trigger actions.

Live runs use your available balance. Review current pricing and account usage before running large batches.

Choice → a route

Use choice as the selected label. Inspect probabilities to see whether alternatives are close.

Yes / No → a threshold

noul: 0.96 means an estimated 96% probability of yes. Choose a threshold based on the cost of mistakes in your workflow.

Score → your rubric

Match the numeric score to its legend. A 3 on this four-level scale is different from 3 on a five-star scale.

Use the same decision through the API

Keep your state and questions. Send them from your server with a Jev AI API key.

1. Create a keyJev API → Your Jev API keys

2. Set an environment variableJEV_AI_API_KEY on your server

3. Send your requestPOST /api/v1/systemone

In the playground, API code generates cURL, JavaScript or Python from your current input. The example below sends the complete support-triage case. Running it makes a live, metered API call; the tutorial itself does not.

curl --fail-with-body https://jev-ai.pro/api/v1/systemone \
  -H "Authorization: Bearer $JEV_AI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "jev-latest",
  "state": "Hi, this is the third time I am writing. Our payouts have failed every day since Monday and my team cannot pay suppliers. I already re-entered the bank details twice. If this is not fixed today we will have to move to another provider.",
  "questions": {
    "team": {
      "type": "choice",
      "instructions": "Which team should handle this ticket?",
      "criteria": {
        "billing": "Payments, payouts, invoices and refunds",
        "technical": "Bugs, outages, integrations and API errors",
        "sales": "Pricing, upgrades and new accounts",
        "account": "Login, profile and permissions"
      }
    },
    "urgent": {
      "type": "noul",
      "instructions": "Does the customer need a response today?"
    },
    "frustration": {
      "type": "score",
      "instructions": "How frustrated is the customer?",
      "criteria": [
        "Calm",
        "Mildly annoyed",
        "Frustrated",
        "Angry and ready to churn"
      ]
    },
    "churn_risk": {
      "type": "noul",
      "instructions": "Does the customer threaten to leave or switch providers?"
    }
  }
}'

Set the environment variable before running the example. Keep the key on your server. Jev AI keys authenticate this site's endpoint; an official TypeSafe endpoint requires its own key. New to keys? Follow how to get a Jev API key.

Create a Jev AI API key Request, response & error reference

Using the TypeSafe AI SDK

Keep the SDK client pointed at the service whose key and balance you use.

The @typesafe-ai/sdk package is published by TypeSafe AI. For this platform, set baseURL: 'https://jev-ai.pro/api' and a server-side Jev AI key. Changing only the key leaves the destination unchanged.

Follow the TypeSafe AI SDK setup example for configuration and error handling. For the official TypeSafe AI service, follow its own documentation instead. Never place an API key in browser code.

When something does not work

Check the request and account state before repeating a call.

What you see	What to check
401 · Authentication	Send a valid Jev AI key in the Bearer header and confirm it has not been revoked.
402 · Balance	Check your available balance and account usage on the Jev API page.
422 · Validation	Check state, question types, unique question IDs, criteria and request limits.
429 · Capacity or rate limit	Respect Retry-After when present and reduce concurrency.
502 / 504 · Upstream failure	Check the error and recorded usage. Avoid blindly replaying a request when its outcome is uncertain.

TypeSafe AI and Jev FAQ

What is TypeSafe AI, and how is it related to Jev?

TypeSafe AI develops Jev, a System One model for typed decisions. This tutorial uses the independent Jev AI playground to show how to ask questions and work with the returned probabilities.

Is this the official TypeSafe AI website?

No. TypeSafe AI operates typesafe.ai and its own console and API. Jev AI operates this playground and API independently. Choose the service you intend to use before creating an account, obtaining a key or purchasing usage.

Can I use the TypeSafe AI SDK with this endpoint?

The official JavaScript / TypeScript SDK supports a configurable baseURL. To use it with Jev AI, set baseURL to https://jev-ai.pro/api and supply a Jev AI key on your server. Our API reference includes the complete setup. A TypeSafe AI account key belongs to the official service instead.

Do I need an account to use Jev?

You can inspect the recorded examples without making a live request. Sign in to run your own text in the playground. An API call requires a Jev AI API key and an available balance.

Does switching the tutorial tabs run the model?

No. This tutorial displays the support-triage recording dated September 18, 2026. Switching tabs only changes which recorded answer is shown. Run your own case in the playground for a fresh result.

Can I send images or audio to Jev?

This tutorial covers text decisions with Jev. OmniJev and Jev-Omni are separate multimodal projects; their model guides describe their own inputs and setup.

Why did my Score answer contain a decimal?

Score answers are probability-weighted across the ordered levels you defined. A result between levels is expected. Read the returned legend and probabilities rather than treating every score as an integer label.

Try your first decision

Start with the support example, then change one input at a time.

Open the playground

This guide describes the Jev AI playground and API. For the separate multimodal projects, see OmniJev and Jev-Omni.