> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.ada.cx/docs/optimization/testing/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.ada.cx/_mcp/server.

# Testing

> **Tip**
>
> **Not sure where to begin?** Explore our [Getting started](/docs/welcome/getting-started) guidelines to set up your first AI Agent, review [Key concepts](/docs/welcome/key-concepts) to understand the essentials, or check out [Improvement tactics](/docs/welcome/improvement-tactics) to resolve issues and keep things running smoothly.

Testing plays an important role in building a reliable AI Agent and is a [key concept](/docs/welcome/key-concepts) in Ada.

> **Note**
>
> Before getting started to test your AI Agent, make sure its core elements—like [Knowledge](/docs/knowledge), [Actions](/docs/automation/tools/api-tools), and [Processes](/docs/automation/processes)—are in place. Other core features may also apply depending on your setup. To learn more, see the [Getting started](/docs/welcome/getting-started) section.

This section covers two approaches to testing:

* **[Interactive Testing](/docs/optimization/testing/interactive-testing)**: Interact with your AI Agent in real time to experience responses as an end user would. You'll learn [how to get started with testing](/docs/optimization/testing/interactive-testing#start-testing), [open the test chat in a new window or browser](/docs/optimization/testing/interactive-testing#test-chat-options), [impersonate different user types](/docs/optimization/testing/interactive-testing#impersonate-user-types), and [reset or end a test chat](/docs/optimization/testing/interactive-testing#reset-end-chat).

* **[Simulations](/docs/optimization/testing/simulations)**: [Create](/docs/optimization/testing/simulations#create-a-test-case-2) and [run](/docs/optimization/testing/simulations#run-simulations) test cases to understand how changes to your AI Agent configuration impact behavior. Define [expected outcomes](/docs/optimization/testing/simulations/best-practices#expected-outcomes), run simulations against your AI Agent, and [review pass/fail results](/docs/optimization/testing/simulations#review-results) with detailed rationale.

---

Have any questions? Contact your Ada team, or email us at [](mailto:help@ada.cx?subject=Help%20Docs%20inquiry).

> Overview

## Docs

- [Interactive Testing](https://docs.ada.cx/docs/optimization/testing/interactive-testing.md)
- [Simulations](https://docs.ada.cx/docs/optimization/testing/simulations.md)
- [Best practices](https://docs.ada.cx/docs/optimization/testing/simulations/best-practices.md)