---
title: ModelJudgePrompt
framework: evaluations
role: symbol
role_heading: Structure
path: evaluations/modeljudgeprompt
---

# ModelJudgePrompt

A configuration for how a model-as-judge evaluator constructs its prompt.

## Declaration

```swift
struct ModelJudgePrompt<Input> where Input : ModelSampleProtocol
```

## Mentioned in

Scoring with model-as-judge evaluators

## Overview

Overview let prompt = ModelJudgePrompt<ModelSample<String>>(     instructions: "You are a domain expert evaluating product reviews." ) ModelJudgePrompt bundles the instructions, response presentation, and reference-data injection into a single composable value. Use it with ModelJudgeEvaluator to customize how the model as judge sees the evaluation.

## Topics

### Creating a prompt configuration

- [init(instructions:evaluationTarget:reference:)](evaluations/modeljudgeprompt/init(instructions:evaluationtarget:reference:).md)
- [defaultInstructions](evaluations/modeljudgeprompt/defaultinstructions.md)

### Customizing judge input

- [instructions](evaluations/modeljudgeprompt/instructions.md)
- [evaluationTarget](evaluations/modeljudgeprompt/evaluationtarget.md)
- [reference](evaluations/modeljudgeprompt/reference.md)

## Relationships

### Conforms To

- [Sendable](swift/sendable.md)
- [SendableMetatype](swift/sendablemetatype.md)

## See Also

### Model-as-judge evaluations

- [Designing effective model-as-judge evaluators](evaluations/designing-effective-model-judges.md)
- [Scoring with model-as-judge evaluators](evaluations/scoring-with-model-as-judge-evaluators.md)
- [ModelJudgeEvaluator](evaluations/modeljudgeevaluator.md)
- [ScoreDimension](evaluations/scoredimension.md)