Migrating from Vizra ADK

The ADK’s evaluation system (legacy docs) ran single-pass CSV evals against ADK agents and wrote CSV results. Vizra Evals is its successor, rebuilt on the official Laravel AI SDK: sampled runs, database persistence, baselines, and a dashboard. It’s a reposition, not a rename — the concepts map, the code changes.

The mapping

Vizra ADK	Vizra Evals
`public string $agentName = 'support'` + `Agent::run()`	A `laravel/ai` agent target: `target(): mixed` or `expect(SupportBot::class)`
`BaseEvaluation` subclass required	Optional — inline `toPassEval()` covers most evals; classes remain for matrices
`preparePrompt(array $csvRowData): string`	`transform(Row $row): Row` (optional; preserves row identity)
`evaluateRow(array $row, string $llmResponse)`	`evaluate(Row $row, AgentResponse $response)` — the full response object, not a string
`$this->assertResponseContains($response, 'x')`	`$this->assertContains('x')` — the response is ambient; no parameter threading
CSV datasets only	JSONL (preferred), CSV still supported, arrays, Eloquent, production conversations
One run per row, pass/fail	`samples(n)` — pass rates and score distributions (scoring)
`vizra:run:eval` + CSV output in `storage/`	`evals:run` / `pest --evals` + database + dashboard + `--output=json`
Always exit 0	Exit codes gate CI: 0/1/2 (CLI)
`assertLlmJudge*` with regex response parsing	`judge()` on structured output — no parsing, reasoning persisted, calibration

Renamed for honesty

Old	New	Why
`assertNotToxic`	`containsNoBlockedWords`	It’s a wordlist — the name now says so
`assertNoPII`	`noObviousPII`	Regex-grade detection, named accordingly

Removed — deliberately

assertResponseHasPositiveSentiment (keyword counting), assertGrammarCorrect (regex heuristics), and assertReadabilityLevel (hand-rolled Flesch-Kincaid) measured nothing real. Each is one properly-done judge call away:

The honest replacement

->judge('The response reads as positive and professionally written.', min: 7)

A worked migration

Before — ADK

class SupportEvaluation extends BaseEvaluation
{
    public string $agentName = 'customer_support';
    public string $csvPath = 'app/Evaluations/data/support.csv';

    public function evaluateRow(array $csvRowData, string $llmResponse): array
    {
        $this->resetAssertionResults();
        $this->assertResponseContains($llmResponse, $csvRowData['expected_response']);
        // ... manual final_status bookkeeping
    }
}

After — Vizra Evals

it('handles support questions', function () {
    expect(SupportBot::class)->toPassEval(fn ($eval) => $eval
        ->dataset(base_path('evals/support.jsonl'))
        ->samples(3)
        ->assert(fn ($a, $row) => $a->contains($row->expected()))
        ->judge('Answers accurately without inventing policy.', min: 7)
        ->gate(maxRegressions: 0)
    );
});

No manual resets, no status bookkeeping, no CSV parsing — and the run is recorded, baselined, and visible in the dashboard.

Your ADK agents need porting to the Laravel AI SDK to be evaluated directly (the SDK’s Agent contract + Promptable). Until then, the Closure target is the bridge — wrap anything that can produce an AgentResponse.

Getting Started

Core Concepts

Writing Evals

Running & CI

Dashboard

Migration

Migrating from Vizra ADK

The mapping

Renamed for honesty

Removed — deliberately

A worked migration

​The mapping

​Renamed for honesty

​Removed — deliberately

​A worked migration

The mapping

Renamed for honesty

Removed — deliberately

A worked migration