TypeSafe AI Jev observability

Overview

Laminar is an open-source, OpenTelemetry-native observability platform for AI agents. Trace, debug, and monitor every TypeSafe AI Jev call your agent makes, with the state, the questions you asked, the typed answers, and token usage on each span, in both TypeScript and Python. Jev is TypeSafe AI’s System One model. Instead of generating text, it reads your application state and answers typed questions: a yes/no probability (Noul), a selected option (Choice), or a rubric score (Score). Agents use it for routing, guardrails, and scoring, so these are exactly the decisions you want visible in a trace. Laminar auto-instruments the TypeSafe SDK: initialize Laminar once and every System One call is traced.

Getting Started

Jev is in early access: create your key in the TypeSafe console. No account yet? Use an OpenRouter API key with TYPESAFE_BASE_URL=https://openrouter.ai/api instead.

TypeScript
Python

1. Install Laminar and the TypeSafe SDK

npm install @lmnr-ai/lmnr@latest @typesafe-ai/sdk

2. Set up your environment variables

Store your API keys in a .env file:

# .env file
LMNR_PROJECT_API_KEY=your-laminar-project-api-key
TYPESAFE_API_KEY=your-typesafe-api-key

Then load them in your application using a package like dotenv.

3. Initialize Laminar

@typesafe-ai/sdk is loaded as an ES module in most projects, so pass the client class to instrumentModules for Laminar to patch it:

import { Laminar } from '@lmnr-ai/lmnr';
import { TypeSafeClient } from '@typesafe-ai/sdk';
import 'dotenv/config';

Laminar.initialize({
  instrumentModules: { typesafe: TypeSafeClient },
});

const client = new TypeSafeClient({ defaultModel: 'jev-1.13.0' });

4. Use the TypeSafe SDK as usual

import { choice, noul } from '@typesafe-ai/sdk';

const result = await client.systemOne({
  state:
    'I was charged twice for my annual plan. Please refund one of the charges.',
  questions: {
    wants_refund: noul('Does the customer ask for money back?'),
    queue: choice('Which team should handle this?', {
      billing: 'Charges, invoices, refunds',
      technical: 'Bugs and integration problems',
      other: null,
    }),
  },
});

console.log(result.answers.wants_refund.noul);
console.log(result.answers.queue.choice);

All systemOne calls are now traced in Laminar.

1. Install Laminar and the TypeSafe SDK

pip install -U lmnr typesafe-sdk python-dotenv

2. Set up your environment variables

Store your API keys in a .env file:

# .env file
LMNR_PROJECT_API_KEY=your-laminar-project-api-key
TYPESAFE_API_KEY=your-typesafe-api-key

3. Initialize Laminar

Laminar instruments the TypeSafe SDK automatically when the typesafe-sdk package is installed:

import os

from dotenv import load_dotenv
from lmnr import Laminar
from typesafe_sdk import TypeSafeClient

load_dotenv()

Laminar.initialize()

client = TypeSafeClient(model="jev-1.13.0")

4. Use the TypeSafe SDK as usual

from typesafe_sdk import Choice, Noul

response = client.system_one(
    state="I was charged twice for my annual plan. Please refund one of the charges.",
    questions={
        "wants_refund": Noul(instructions="Does the customer ask for money back?"),
        "queue": Choice(
            instructions="Which team should handle this?",
            criteria={
                "billing": "Charges, invoices, refunds",
                "technical": "Bugs and integration problems",
                "other": None,
            },
        ),
    },
)

print(response.answers["wants_refund"].noul)
print(response.answers["queue"].choice)

All system_one calls are now traced in Laminar, including calls made with AsyncTypeSafeClient.

What Laminar captures

Each call becomes an LLM span named typesafe.system_one. Every span carries:

The model that answered (jev-1.13.0, or the resolved default when you rely on jev-latest).
The state you sent, shown as the span input.
The full question set: instructions and criteria for every Noul, Choice, and Score.
The typed answers, shown as the span output, with probabilities and confidence intact.
Input and output token counts.

Failed calls (an unknown model name, an authentication error) are marked as errors on the span with the exception recorded, so a misconfigured guardrail shows up in the trace instead of disappearing into a retry loop.

TypeSafe AI Jev trace in Laminar with typed answers on the system_one span — A support agent trace: the selected Jev span carries the typed answers, with the chosen queue, urgency probability, and rubric score on the span output and the question set in the output schema. The drafted reply and a second Jev verification call sit inline in the same trace.

See what happened in a trace

Open a trace in Laminar and you land on the transcript view: Laminar extracts the agent input, the model’s turns, and any tool calls into a conversation, so you read what happened instead of clicking through a tree of span names. A Jev call sits inline with the LLM calls it routes or guards, so you can see the classification next to the action it triggered. More on the trace UX: Viewing traces.

Track outcomes with Signals

Traces answer what happened on this run. Signals answer the cross-trace question: how often does the guardrail fire, which queue gets the most tickets, when does confidence drop below the threshold you tuned for. A Signal pairs a plain-language prompt with a JSON output schema. Laminar runs it live on new traces (Triggers) or backfills it across history (Jobs) and records a structured event every time it matches. From there you query, cluster, and alert on events across every trace.

Query across traces

SQL editor for ad-hoc queries across traces, spans, signals, and evals.
SQL API for programmatic access from scripts and pipelines.
CLI (lmnr-cli sql query) for terminal-driven queries and piping JSON into shell tools or coding agents.
MCP server to query Laminar directly from Claude Code, Cursor, Codex, or any MCP-aware client.

Enrich your TypeSafe traces

Attach sessions, user IDs, metadata, and tags to TypeSafe spans via the SDK reference.
Wrap the functions around your Jev calls with observe and mark them as TOOL spans so they show up in the transcript.
Set LMNR_TRACE_CONTENT=false to keep the model and token counts while omitting state, questions, and answers from spans.

What’s next

Viewing traces

Read the transcript view, filter, and search across traces.

Signals

Detect behaviors and failures across every run, then query, cluster, and alert on them.

SQL editor and MCP server

Query traces programmatically from the UI, API, or your IDE.

Tracing structure

Add sessions, metadata, and tags, and group calls under your own spans.

OpenAI

Trace the OpenAI SDK directly in TypeScript and Python.

Anthropic

Trace the Anthropic SDK directly in TypeScript and Python.

LiteLLM

One integration for every model LiteLLM routes to.

OpenRouter

Trace any model called through OpenRouter, Jev included.

Gemini

Trace Gemini calls made with the Google Gen AI SDK.

All integrations

Browse every provider, framework, coding agent, and browser integration Laminar supports.

Overview

LLM provider SDKs

Agent frameworks

Coding agents

Browser and computer-use agents

Other platforms

OpenTelemetry

Overview

Getting Started

1. Install Laminar and the TypeSafe SDK

2. Set up your environment variables

3. Initialize Laminar

4. Use the TypeSafe SDK as usual

1. Install Laminar and the TypeSafe SDK

2. Set up your environment variables

3. Initialize Laminar

4. Use the TypeSafe SDK as usual

What Laminar captures

See what happened in a trace

Track outcomes with Signals

Query across traces

Enrich your TypeSafe traces

What’s next

Viewing traces

Signals

SQL editor and MCP server

Tracing structure

OpenAI

Anthropic

LiteLLM

OpenRouter

Gemini

All integrations

​Overview

​Getting Started

​1. Install Laminar and the TypeSafe SDK

​2. Set up your environment variables

​3. Initialize Laminar

​4. Use the TypeSafe SDK as usual

​1. Install Laminar and the TypeSafe SDK

​2. Set up your environment variables

​3. Initialize Laminar

​4. Use the TypeSafe SDK as usual

​What Laminar captures

​See what happened in a trace

​Track outcomes with Signals

​Query across traces

​Enrich your TypeSafe traces

​What’s next

Viewing traces

Signals

SQL editor and MCP server

Tracing structure

​Related integrations

OpenAI

Anthropic

LiteLLM

OpenRouter

Gemini

All integrations

Overview

Getting Started

1. Install Laminar and the TypeSafe SDK

2. Set up your environment variables

3. Initialize Laminar

4. Use the TypeSafe SDK as usual

1. Install Laminar and the TypeSafe SDK

2. Set up your environment variables

3. Initialize Laminar

4. Use the TypeSafe SDK as usual

What Laminar captures

See what happened in a trace

Track outcomes with Signals

Query across traces

Enrich your TypeSafe traces

What’s next

Related integrations