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

# Run and review

> Execute simulation tests, inspect results, and organize tests into sets.

## Test sets

A test set is a named collection of test cases. Use sets to cover a feature area or release scope (for example, "Payments," "Shipping," "Core intents"). A test case can belong to **multiple** sets.

To create a set:

1. Go to **Testing > Test Sets** and select **New set**.
2. Give the set a **name** and add cases from the picker.

<Tip>
  Create focused sets ("Refunds," "Shipping address changes," "Escalations") so failures point straight to the right area.
</Tip>

## Run tests

<Note>
  Tests run against non-production versions. Select **Draft** or **Sandbox** when you start a run.
</Note>

You can run a **single case** or an entire **set**.

<Tabs>
  <Tab title="Single case">
    1. Open the case in **Test Cases**.
    2. Choose **Draft** or **Sandbox**.
    3. Select **Run** to execute just this scenario.

    The case shows **Outcome** and **Last run** after completion.

    <img src="https://mintcdn.com/polyai/Qu880HppNqT19Eyr/images/analytics/test-case-run-from-menu.png?fit=max&auto=format&n=Qu880HppNqT19Eyr&q=85&s=da4556b264e8a4a9096efc92dd014191" alt="Run case from menu" width="1820" height="1092" data-path="images/analytics/test-case-run-from-menu.png" />
  </Tab>

  <Tab title="Test set">
    1. Open the set in **Test Sets** and select **Run set**.
    2. Choose **Draft** or **Sandbox**.
    3. Start the run to execute all member cases together.

    The set displays an aggregated view with pass/fail counts and trend charts.

    <img src="https://mintcdn.com/polyai/Qu880HppNqT19Eyr/images/analytics/test-runs-completed.png?fit=max&auto=format&n=Qu880HppNqT19Eyr&q=85&s=764f674b0365192dc550eeb5dc6797e1" alt="Completed runs" width="1850" height="974" data-path="images/analytics/test-runs-completed.png" />
  </Tab>
</Tabs>

## Review results

When a run completes, select it to open the **Test run** panel. The panel shows:

* **Prompt assertions** — each assertion with a pass/fail indicator and a short explanation of why it passed or failed.
* **Conversation** — the full transcript of the simulated conversation, showing both caller and agent turns.

<img src="https://mintcdn.com/polyai/zdYy6ORmlm_2Hesc/images/analytics/sim-test-run-results.png?fit=max&auto=format&n=zdYy6ORmlm_2Hesc&q=85&s=aba26104c8cfbeb78fd28693a3f4b6b6" alt="Test run results" width="2490" height="1484" data-path="images/analytics/sim-test-run-results.png" />

For test sets, the set view provides:

* **Pass/fail counts** – how many cases succeeded vs. failed in the run.
* **Trend charts** – historical pass/fail rates across multiple runs, so you can spot regressions over time.

If a previously passing test case fails after a change, review the conversation transcript to identify what broke. Common causes include:

* Knowledge topic changes that altered routing
* Function logic updates that changed return values
* Flow modifications that skipped or reordered steps

## Edit test case parameters

Each test case stores the function call values from the original conversation. You can edit these to test variations of the same scenario without creating a new case.

1. Open the test case from **Test Cases**.
2. Select the parameters you want to modify.
3. Adjust values to simulate a different scenario – for example, change a date, customer ID, or location.
4. Save the case.

<Tip>
  Editing parameters is useful for testing edge cases. For example, duplicate a booking test case and change the party size to test large-group handling.
</Tip>

## Best practices

* **Create focused sets** – group cases by feature area so failures point to the right area.
* **Re-run after knowledge changes** – topic edits can silently break other flows. Test sets catch this.
* **Run after every significant change to Draft** – catching regressions early saves time and prevents issues from reaching Sandbox or Live.