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

# Test

> Evaluate and test agent quality at scale with datasets, evaluators, prompts, and Studio.

<div class="home-page mx-auto max-w-8xl px-0 lg:px-5" style={{ paddingBottom: "8rem" }}>
  <div class="mdx-content prose prose-gray dark:prose-invert mx-4 pt-10">
    <h1 class="flex whitespace-pre-wrap group font-semibold text-2xl sm:text-3xl mt-8">Test</h1>

    LangSmith's testing tools help you measure agent quality, iterate on prompts, and debug live in an interactive environment.

    <h2 class="flex whitespace-pre-wrap group font-semibold">Get started</h2>

    <Steps>
      <Step title="Create an account" icon="user-plus">
        Sign up at [smith.langchain.com](https://smith.langchain.com?utm_source=docs\&utm_medium=cta\&utm_campaign=langsmith-signup\&utm_content=snippets-langsmith-account-api-key-quickstart) (no credit card required).
        You can log in with **Google**, **GitHub**, or **email**.
      </Step>

      <Step title="Create an API key" icon="key">
        Go to your [Settings page](https://smith.langchain.com/settings) → **API Keys** → **Create API Key**.
        Copy the key and save it securely.
      </Step>
    </Steps>

    Once your account and API key are ready, [run your first evaluation](/langsmith/evaluation-quickstart).

    <h2 class="flex whitespace-pre-wrap group font-semibold">Explore testing tools</h2>

    <CardGroup cols={2}>
      <Card title="Evaluation" cta="Run an evaluation" href="/langsmith/evaluation" icon="chart-bar">
        Create datasets, define evaluators, and run experiments to measure agent quality over time.
      </Card>

      <Card title="Prompt engineering" cta="Author prompts" href="/langsmith/prompt-engineering" icon="edit">
        Author, version, and collaborate on prompts in the Prompt Hub and playground.
      </Card>

      <Card title="Context Hub" cta="Open the Context Hub" href="/langsmith/context-hub" icon="book">
        Manage versioned instructions and tools your agents use, and promote them across environments.
      </Card>

      <Card title="Studio" cta="Open Studio" href="/langsmith/studio" icon="window">
        Use an interactive environment for developing and debugging agents.
      </Card>
    </CardGroup>

    <Card title="Find and fix failures with Engine" icon="https://mintcdn.com/langchain-5e9cc07a/auWE6_dMRp183OCf/images/brand/engine-icon-no-bg-dark.svg?fit=max&auto=format&n=auWE6_dMRp183OCf&q=85&s=dd41aef3ce789c1a04ea3c37b5903eac" href="/langsmith/engine-overview" arrow="true" width="63" height="63" data-path="images/brand/engine-icon-no-bg-dark.svg">
      When evaluations surface failures, use LangSmith Engine to diagnose the root cause and resolve them.
    </Card>
  </div>
</div>

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/test-overview.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>