---
title: "Agent Judges"
description: "Use natural-language rubrics to evaluate traces and examples with structured results and supporting evidence."
sidebar:
  label: "Agent judges"
seo:
  title: "Agent Judges | Judgment Docs"
  description: "Learn how Agent Judges use natural-language rubrics, then create one for reusable evaluation."
---

An Agent Judge evaluates a trace or example against a natural-language rubric.
It returns a structured value with reasoning and evidence from the evaluated
input. Use one when the criterion requires interpretation rather than a fully
deterministic rule.

## Create an Agent Judge

This workflow creates a reusable rubric-based judge.

### Prerequisites

- A Judgment project where you can create judges

1. ### Choose the output type

    Open **Judges**, select **New Judge**, then choose **Create manually**.

    Select the output contract that matches the decision you need:

    - **Binary** for a true-or-false criterion
    - **Classification** for one choice from a defined set
    - **Score** for a numeric value within a range

    This guide uses **Binary**.

2. ### Define the rubric

    Name the judge `Grounded answer` and add a description that tells teammates
    when to use it. Keep the default reasoning level for the first run.

    Enter this prompt:

    ```text
    Return true when the response is supported by information retrieved in the
    trace. Return false when the response makes a claim that the retrieved
    information does not support. Explain the evidence for the decision.
    ```

    Select **Create Judge**. Judgment opens the new judge detail page.

The judge now exists as a reusable project asset. Creating it does not enable
continuous online evaluation.

## Create the same kind of judge from the SDK

Use the SDK when the judge definition should live beside application or
infrastructure code.

**Python**

```python title="create_agent_judge.py"
from judgeval import Judgeval


client = Judgeval(project_name="my-project")

judge = client.agent_judges.create(
    name="Grounded answer",
    prompt=(
        "Return true when the response is supported by information "
        "retrieved in the trace. Explain the evidence."
    ),
    model="gpt-5.2",
    score_type="binary",
)

print(judge.judge_id)
```

**TypeScript**

```typescript title="createAgentJudge.ts"
import { Judgeval } from "judgeval";

const client = await Judgeval.create({ projectName: "my-project" });

const judge = await client.agentJudges.create({
  name: "Grounded answer",
  prompt:
    "Return true when the response is supported by information " +
    "retrieved in the trace. Explain the evidence.",
  model: "gpt-5.2",
  scoreType: "binary",
});

console.log(judge.judgeId);
```

After SDK creation, open **Judges** and select `Grounded answer` to review its
configuration.

## Next step

To run a binary or categorical judge on incoming traffic, [create and monitor
a behavior](/documentation/judges/behavior-setup). To keep the judge on demand,
apply it only from your agent or test workflow.