> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vizra.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Class-Based Evaluations

> The full authoring surface — reusable suites, model matrices, and transform hooks.

Inline `toPassEval()` config covers most evals. Reach for a class when a suite deserves a name of its own, needs a **model matrix**, or should be runnable from the [CLI](/evals/cli) and the [dashboard's](/evals/dashboard) Run button.

```bash Terminal theme={null}
php artisan make:eval SupportQuality
```

```php app/Evals/SupportQuality.php theme={null}
use App\Agents\SupportBot;
use Laravel\Ai\Responses\AgentResponse;
use Vizra\Evals\Dataset\Dataset;
use Vizra\Evals\Dataset\Row;
use Vizra\Evals\Evaluation;
use Vizra\Evals\Run\Gate;

class SupportQuality extends Evaluation
{
    public int $samples = 3;

    public function target(): mixed
    {
        return SupportBot::class;   // class-string, instance, or Closure(Row): AgentResponse
    }

    public function dataset(): Dataset
    {
        return Dataset::fromJsonl(base_path('evals/support.jsonl'));
    }

    public function evaluate(Row $row, AgentResponse $response): void
    {
        $this->assertNotEmpty()->gate();
        $this->assertContains($row->expected());
        $this->assertCostBelow(0.02);

        $this->judge()
            ->criteria('Answers using only documented store policy.')
            ->minScore(7);
    }

    public function gatePolicy(): ?Gate
    {
        return new Gate(minScore: 0.8, maxRegressions: 0);
    }
}
```

Inside `evaluate()`, the current response and row are ambient — assertion helpers take no `$response` argument, and every helper from the [assertions reference](/evals/assertions) exists as `$this->assert*()`.

## Model matrices with `across()`

Run the whole dataset against multiple provider/model combos — each becomes its own series in results, comparisons, and the dashboard:

```php Compare models on your own data theme={null}
public function across(): array
{
    return [
        ['provider' => 'openai', 'model' => 'gpt-5.4'],
        ['provider' => 'anthropic', 'model' => 'claude-sonnet-5'],
    ];
}
```

This is how you answer "can we move to the cheaper model?" with your own dataset instead of someone else's benchmark.

## Transform hooks

Rewrite rows before they reach the agent — keeping row identity intact:

```php Prompt wrapping theme={null}
public function transform(Row $row): Row
{
    return $row->withInput("Customer message:\n{$row->input}");
}
```

<Info>
  Use `$row->withInput()` (and friends) rather than constructing new rows — they preserve the content hash, so [baseline comparison](/evals/baselines-and-regressions) still lines up across runs even as your transform evolves.
</Info>

## Running class-based suites

```php From Pest — recorded under the class name theme={null}
expect(SupportBot::class)->toPassEval(fn ($eval) => $eval->using(SupportQuality::class));
```

```bash From the CLI theme={null}
php artisan evals:run SupportQuality
```

And from the dashboard's **Run** button, which executes discovered classes via a queued job. All three surfaces share the tables, baselines, and history.