<!--
{
  "availability" : [
    "Xcode: 27.0.0 -",
    "iOS: 27.0.0 -",
    "iPadOS: 27.0.0 -",
    "macCatalyst: 27.0.0 -",
    "macOS: 27.0.0 -",
    "visionOS: 27.0.0 -",
    "watchOS: 27.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "Evaluations",
  "identifier" : "/documentation/Evaluations/ModelJudgeEvaluator/judgePrompt(for:output:)",
  "metadataVersion" : "0.1.0",
  "role" : "Instance Method",
  "symbol" : {
    "kind" : "Instance Method",
    "modules" : [
      "Evaluations"
    ],
    "preciseIdentifier" : "s:11Evaluations19ModelJudgeEvaluatorV11judgePrompt3for6output16FoundationModels0F0Vx_13ExpectedValueQztYaKF"
  },
  "title" : "judgePrompt(for:output:)"
}
-->

# judgePrompt(for:output:)

Builds and returns the full judge prompt for inspection, debugging, or logging.

```
nonisolated(nonsending) func judgePrompt(for sample: Input, output: Input.ExpectedValue) async throws -> Prompt
```

## Parameters

`sample`

The evaluation sample.

`output`

The model’s response content.

## Return Value

The fully assembled `Prompt` to send to the model judge.

## Discussion

Use this to inspect exactly what the model judge receives for a given input and response pair.

---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)