> ## 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.

# Multi-Turn Conversations

> Evaluate agents in the middle of a conversation — including conversations from production.

Real support and chat agents don't answer isolated prompts — they answer *turn seven*, with six turns of context behind them. Vizra Evals replays that context for real.

## Multi-turn rows

```json evals/support.jsonl theme={null}
{"messages": [
  {"role": "user", "content": "Hi, I ordered a lamp last week"},
  {"role": "assistant", "content": "Thanks for reaching out! How can I help with your lamp?"},
  {"role": "user", "content": "Can I still return it?"}
], "expected": "30 days"}
```

The final entry must be a `user` turn — it becomes the prompt. Everything before it is replayed as genuine conversation history through the Laravel AI SDK's conversation channel, so the agent responds exactly as it would mid-conversation in production: aware the customer bought a lamp, answering "can I return **it**" correctly.

<Info>
  Replay is real, not prompt-stuffing: prior turns are hydrated into SDK `Message` objects and delivered through the same mechanism the SDK uses for stored conversations. The agent's instructions, tools, and middleware all still apply.
</Info>

## Replaying production traffic

If your agents use the SDK's conversation persistence (`RemembersConversations`), your `agent_conversations` tables are a free eval dataset:

```php tests/Evals/SupportBotTest.php theme={null}
expect(SupportBot::class)->toPassEval(fn ($eval) => $eval
    ->fromConversations(take: 50)
    ->judge('At least as helpful and accurate as the reply we actually sent.')
);
```

For each stored conversation of this agent: the latest user turn becomes the prompt, everything before it replays as context, and **the reply your agent actually gave** becomes `$row->expected()`. Two powerful patterns fall out:

```php Judge against the production answer theme={null}
->judge('Answers the customer at least as well as the reference reply.', min: 7)
// the judge sees $row->expected() as reference information automatically
```

```php Regression-test a prompt change against real traffic theme={null}
->fromConversations(take: 100)
->samples(2)
->gate(maxRegressions: 0)
// first run baselines real traffic; future prompt changes diff against it
```

The standalone form gives you query refinement: `Dataset::fromConversations(SupportBot::class)->latest()->take(50)->where('title', 'like', '%refund%')`.

<Warning>
  Eval runs **never write** to your conversation tables — replay is read-only by construction, so running evals can't pollute production history.
</Warning>

## Assertion behavior on multi-turn rows

Everything works the same: `$row->input` is the final user turn, `$row->messages` holds the prior turns, and all [assertions](/evals/assertions) run against the agent's real `AgentResponse`. In the recorded results and dashboard, multi-turn rows display as the final question with a "(after N prior turns)" marker rather than a wall of JSON.