---
title: "judgePrompt(for:output:)"
framework: evaluations
role: symbol
role_heading: Instance Method
path: "evaluations/modeljudgeevaluator/judgeprompt(for:output:)"
---

# judgePrompt(for:output:)

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

## Declaration

```swift
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

Return Value The fully assembled Prompt that would be sent to the judge.

## Discussion

Discussion Use this to see exactly what the judge model will receive for a given input/response pair.

## See Also

### Configuring the judge prompt

- [defaultInstructions](evaluations/modeljudgeevaluator/defaultinstructions.md)
