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

# Test Mode

> Run an agent Flow with data from past tasks in a safe environment before you publish.

Test mode lets you validate an agent Flow with data from past tasks before you publish it. Beam runs tests in a safe environment: integrations are sandboxed, so test runs do not create, update, or delete live records.

<Frame>
  <img src="https://mintcdn.com/beamai/JHnoCEC4zo9vcEgb/03-running-operations/debugging-testing/test-datasets/test-mode-current.jpg?fit=max&auto=format&n=JHnoCEC4zo9vcEgb&q=85&s=e34ff6a77aa615182538d4430451d6f9" alt="Flow header with the Test mode toggle" width="520" height="130" data-path="03-running-operations/debugging-testing/test-datasets/test-mode-current.jpg" />
</Frame>

<h2 id="when-to-use-test-mode">
  When to use test mode
</h2>

Use Test mode when you want to:

* Check Flow changes before publishing them.
* Run a Flow against data from a previous task.
* Review multiple test executions without affecting connected systems.

<h2 id="run-a-test">
  Run a test
</h2>

<Steps>
  <Step title="Open the Flow">
    Open the agent's **Flow**.
  </Step>

  <Step title="Enable Test mode">
    Turn on **Test mode** in the Flow header.
  </Step>

  <Step title="Use a past task as test input">
    Run the Flow with data from a previous task to validate the current Flow configuration without sending changes to live systems.
  </Step>

  <Step title="Review the result">
    Open workspace **Tasks**, then select **Tests** to review test-mode task runs.
  </Step>
</Steps>

<h2 id="what-test-mode-protects">
  What test mode protects
</h2>

* Connected Integrations run in a sandbox while you test, so no live records are created, updated, or deleted.
* You can run as many test executions as you need and review them separately from regular tasks.
* Beam warns you before publishing when live connections are still active.

<h2 id="review-test-runs">
  Review test runs
</h2>

The workspace **Tasks** page has separate **Tasks** and **Tests** tabs. The **Tests** tab includes the current task-list controls, including status and agent filters, a date picker, task-name search, and a View selector.

<h2 id="next-steps">
  Next steps
</h2>

<CardGroup cols={3}>
  <Card title="Debug Tools" icon="bug" href="/03-running-operations/debugging-testing/debug-tools/debug-tools">
    Test an individual node with sample input.
  </Card>

  <Card title="Task Executions" icon="chart-line" href="/03-running-operations/task-management/task-executions/task-executions">
    Review task and test execution details.
  </Card>

  <Card title="Publishing & Deployment" icon="rocket" href="/02-building-agents/advanced-patterns/publishing-deployment/publishing-deployment">
    Publish a validated Flow.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.