Running on jev-latest

See what Jev sees.

Jev is a System One model: it doesn't write prose, it returns typed decisions with calibrated probabilities. Paste any text below and watch nine of them come back in a single request — charted, shareable, and impossible to parse wrong.

~600 ms for nine answers $0.042 per million input tokens No free text to parse

Message X-ray

What is this message actually asking of you?

This becomes the state Jev reads. 0 / 12,000
Public

Appears in Explore and in search results.

Three question types

Everything Jev can answer is one of three shapes. Below, all three are answered against the same eleven-word state — the example straight out of the TypeSafe docs.

"Help! My payouts have been failing for 3 days."

Noul

Does this convey urgency?

Almost certainly
Probability the answer is yes
96%
No Coin flip Yes

A yes/no question comes back as a probability, not a word. 0.96 and 0.51 are different answers, and your code can tell them apart.

How a Noul works

Choice

Which team should handle this?

billing at 96%, from 3 options
96% billing

One option out of a set you define, with the full distribution behind it — so you can see the runner-up and how close it was.

How a Choice works

Score

How frustrated is the customer?

1.24 of 2 · Frustrated

A rating against ordered levels you write. The answer is probability-weighted, so it lands between levels when the text does.

How a Score works
1 request

Nine questions, one call. Jev reads the state once and answers every question against it in parallel.

0 parsing

Answers arrive typed. No JSON mode, no retries on malformed output, no regex over prose.

3 primitives

Noul, Choice, Score. Every decision your software needs is one of these three shapes.

± confidence

Choice and Score carry a confidence value, so "I am not sure" is a branch your code can take.

Coming from an LLM?

The same routing decision written both ways — and where the retry loop goes.

Fresh from the gallery

What other people have been pointing Jev at.

See all →
Message X-ray

Escalate a problem

Urgency: Today · Tone: Strained

Hi — following up on my last two emails. The invoice for March still hasn't been approved and my team can't start the next phase until it clears. I know everyo…

9 answers 388 ms 1 request
Pitch check

By the second sentence

Written for: Technical buyers · Credibility: Unsupported assertions throughout

Jev is a System One model: it doesn't write prose, it returns typed decisions with calibrated probabilities. Paste any text below and watch nine of them come b…

9 answers 324 ms 1 request
Custom questions

Leaning yes: vibe

Written by AI: Probably

Welcome to Echobell, the instant alert app that helps you stay on top of important notifications. Whether you're a developer needing webhook alerts for your CI…

2 answers 389 ms 1 request
Pitch check

Immediately, in the first line

Written for: Business buyers · Credibility: A mix of claims and evidence

Meridian is the operating system for modern logistics teams. We replace the spreadsheet sprawl that runs two trillion dollars of freight with a single collabor…

9 answers 388 ms 1 request
Message X-ray

Share an update

Urgency: No deadline at all · Tone: Warm

Dear Valued Customer You may now view or download the latest monthly e-Statement for your deposit account. Simply log in to OCBC app > Tap "More" at the bottom…

9 answers 281 ms 1 request
Message X-ray

Escalate a problem

Urgency: Right now — everything is blocked · Tone: Strained

Hi — following up on my last two emails. The invoice for March still has not been approved and my team cannot start the next phase until it clears. This is now…

9 answers 339 ms 1 request

Typed decisions, all the way down

Dejev is a demo, not a product. The interesting part is the model underneath — read the TypeSafe docs to put Jev in your own software.