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

# Agent testing & QA

> Find failures before agent changes reach customers. Use scripted Tests and AI-driven Simulations to check responses, routing and tool calls.

## Overview

Agent testing & QA is Voiceflow’s automated testing product for checking customer journeys before release. Replay specific interactions with **Tests** or explore different user replies with AI-driven **Simulations**. A saved conversation can combine both. Check responses, routing and tool calls to find failures and catch regressions after changes.

Open **Tests** from your project sidebar, then **New test** to author either approach in the shared editor. Runs use the selected [Environment](/docs/documentation/deploy/environments/overview); check it before interpreting a result.

A retail Test with its authored conversation and routing check beside the completed run — Review the saved conversation and routing check beside the result of a run.

## Choose a starting point

- **Reproduce a known interaction?** [Write scripted turns](/docs/platform/rehearsal/tests/scripted-turns) and add the response, routing or tool-call checks that define success.
- **Explore different user replies?** [Define a Simulation scenario and success criteria](/docs/platform/rehearsal/simulations/scenarios), then set its conversation turn limit.
- **Try the same behavior with different customer context?** Choose a [starting event](/docs/platform/rehearsal/context/events) and [persona or starting variables](/docs/platform/rehearsal/context/personas).
- **Check several saved conversations after a change?** [Run a batch](/docs/platform/rehearsal/runs/batches) and inspect the failed expectations.

[Compare Tests and Simulations](/docs/platform/rehearsal/tests-vs-simulations) when deciding which approach fits a behavior.

## Explore Agent testing & QA

<a id="explore-rehearsal" />

### [Tests](/docs/documentation/measure/tests)

Make important customer interactions repeatable. Script messages and check responses, routing, tool calls and execution order.

### [Simulations](/docs/platform/rehearsal/simulations/editor)

Explore how an agent handles different user replies. Define the simulated user, success criteria and conversation turn limit.

### [Starting context](/docs/platform/rehearsal/context/personas)

Check behavior for different customers and entry points using personas, starting variables and events.

### [Runs and results](/docs/platform/rehearsal/runs/running)

Find which checks failed and why. Run one conversation or a batch, inspect outcomes and logs, and reopen or retry past runs.

## Continue the testing workflow

<a id="related-areas" />

- **Investigate a failure:** [compare the expected behavior with the conversation, check reasoning and logs](/docs/platform/rehearsal/runs/failures) before changing the agent or its checks.
- **Correct and rerun:** edit the relevant behavior in [Agent studio](/docs/platform/studio), then [retry the affected conversations](/docs/platform/rehearsal/runs/history) in the intended Environment.
- **Extend coverage from production:** use [Transcripts](/docs/documentation/measure/transcripts) to find a real case. [Atlas can turn a conversation into a Test](/docs/changelog/changelog/7#atlas-can-author-convert-and-read-saved-agent-tests-through-) for you to review and run.
- **Automate testing:** use the [QA API reference](/docs/api-reference/sections/qa) for developer-driven execution.

Runs consume credits. See [Credits and costs](/docs/platform/rehearsal/reference/costs) before running broader coverage.
