What is Jev

Jev is actually not a traditional LLM, it doesn’t generate text. It’s what the TypeSafe AI team calls a System One model:

System One models are a class of AI models built to make fast, structured decisions that software can use directly. A System One model evaluates a state and returns typed answers and probabilitie

It’s trained using reinforcement learning for calibrated decisions (RLCD). Your code uses those results to guide what an agent does next, without a full chat LLM call for each decision.

To invoke a Jev model, you send it a state (the context) and questions about that state. Here’s a single-question version of the support-ticket example in their docs:‍

{

  "model": "jev-latest",

  "state": "Hi, I've been trying to connect my Stripe account for 3 days and it keeps failing. I'm losing sales. Please help ASAP.",

  "questions": {

    "is_urgent": {

      "type": "noul",

      "instructions": "The message conveys urgency or time-sensitivity"

    }

  }

}

The docs’ example gives this urgency answer, shown here without the rest of the response:‍

{

  "is_urgent": {

    "type": "noul",

    "noul": 0.999

  }

}

That’s a 99.9% probability that the message is urgent, which your application can use to prioritize the ticket.

There are three types of supported questions:

Choice: Pick from a set of options. Returns a probability for each option and an overall confidence score.

Score: Rate an input against ordered levels, such as low, medium, and high. Returns a continuous score, the underlying distribution, and a confidence value.

Noul: Answer a yes-or-no question. Returns the probability that a statement is true.

LangChain's provider agnostic model is well suited for supporting Jev alongside thousands of other integrations and model providers.

The LangChain integration exposes Jev through TypeSafeClassifier. You pass your state and questions to .invoke(), and get classification results rather than a chat response.

Install langchain-typesafe and set your TYPESAFE_API_KEY, then make a call:‍

from langchain_typesafe import Noul, TypeSafeClassifier

classifier = TypeSafeClassifier()

response = classifier.invoke({

    "state": (

        "The deploy failed twice and customers are seeing 500s. "

        "Can someone look now?"

    ),

    "questions": {

        "urgent": Noul(

            instructions="Does this need attention right now?"

        ),

    },

})

urgency = response.nouls["urgent"].noul

Jev isn’t a drop-in replacement for an LLM. It doesn’t generate text, but it can handle classification tasks we often use LLMs for today, without the same latency and cost. That makes it a promising complement to the model driving your agent: use an LLM for open-ended reasoning and generation, and Jev for fast, structured decisions along the way.