---
title: "Get Started with Judgment"
sidebar:
  label: "Introduction"
seo:
  title: "Get Started with Judgment | Agent Monitoring and Evaluation"
  description: "Learn how Judgment connects production agent traces, investigations, monitoring, and offline tests in one continuous improvement loop."
---

<div class="intro-copy">

Judgment helps teams improve production agents using evidence from real
executions. When something goes wrong, it helps you understand why, measure how
widely it occurs, and verify the change that addresses it.

Agent failures rarely live in the final response alone. They can begin with a
missed tool call, stale context, faulty reasoning, or an execution path that
only appears across a long trace. Judgment keeps the entire execution path
available as evidence.

</div>

## How Judgment works

1. **Capture production executions**

    [Trace](/documentation/tracing) the model calls, tools, state, and
    application logic that make up a complete agent run.

2. **Investigate what went wrong**

    Use [Judgment Agent](/documentation/judgment-agent) to
    search across traces, find related failures, measure their impact, and
    narrow the root cause.

3. **Define what matters**

    Turn the pattern into a [judge](/documentation/judges) with
    [behavior outputs](/documentation/judges/behavior-setup) that you can evaluate
    consistently in production and offline.

4. **Test and monitor the change**

    Preserve representative cases in a [dataset](/documentation/datasets),
    compare test runs, and watch the next release for regressions.

<QuickstartCard title="Quickstart" href="/documentation/quickstart">
  A working trace-and-evaluation loop, proven by a real trace and judge result.
</QuickstartCard>

## Core workflows

<CardGroup cols={2}>
  <Card
    title="Concepts"
    href="/documentation/concepts"
    icon="book-open"
  >
    Learn how traces, judges, behaviors, datasets, tests, and monitoring fit
    together.
  </Card>
  <Card title="Production Monitoring" href="/documentation/monitoring" icon="activity">
    Detect recurring behaviors and get alerted when an agent regresses.
  </Card>
  <Card
    title="Investigate an issue"
    href="/documentation/monitoring/trace-investigation"
    icon="search"
  >
    Move from one failed trace to a pattern, its impact, and a likely cause.
  </Card>
  <Card
    title="Test a change"
    href="/documentation/tests/offline-tests"
    icon="flask-conical"
  >
    Run production-derived cases against a candidate agent before release.
  </Card>
</CardGroup>

## Connect your stack

<CardGroup cols={2}>
  <Card
    title="Tracing"
    href="/documentation/tracing"
    icon="radio"
  >
    Capture complete agent executions from your application.
  </Card>
  <Card
    title="Integrations"
    href="/documentation/integrations"
    icon="network"
  >
    Choose a framework, model provider, or OpenTelemetry integration.
  </Card>
  <Card
    title="MCP server"
    href="/documentation/mcp-and-agent-tools"
    icon="terminal"
  >
    Give coding agents access to Judgment project data and tools.
  </Card>
  <Card title="SDK reference" href="/sdk-reference" icon="book-open">
    Look up the Python and TypeScript APIs.
  </Card>
</CardGroup>