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

# AI Agents

> Autonomous AI testing

QA.tech uses specialized AI agents to test your application like humans would, but faster and more thoroughly. Our system automatically routes testing tasks to the right agent based on context-no manual configuration needed.

## Get Started

<CardGroup cols={2}>
  <Card title="AI Chat Assistant" icon="message-bot" href="/core-concepts/ai-chat-assistant">
    Conversational interface to create, edit, and manage tests.
  </Card>

  <Card title="Create Your First Test" icon="plus" href="/best-practices/creating-tests">
    Write tests in natural language. The AI generates steps automatically.
  </Card>

  <Card title="PR Testing" icon="code-pull-request" href="/pr-testing/overview">
    Review a pull request on a preview environment, or after merge.
  </Card>

  <Card title="Regression Testing" icon="clipboard-list" href="/regression-testing/overview">
    Run a test plan from CI, on a schedule, or by hand.
  </Card>
</CardGroup>

## Our AI Agent System

| Entry point | Purpose | How it runs |
| :- | :- | :- |
| [AI Chat Assistant](/core-concepts/ai-chat-assistant) | Create and edit tests | You start a conversation. The assistant analyzes the application, creates tests for the paths you describe, and shows suggestions for your approval. |
| [PR Testing](/pr-testing/overview) | Change review before or after merge | A review can start when a pull request opens or updates, or when you mention `@qatech` in a comment. It creates tests for new features, runs the relevant tests, and posts the result. |
| [Regression Testing](/regression-testing/overview) | Run a test plan manually, on a schedule, or from CI or the API | You choose the tests. The plan runs them from the app, a cron schedule, a pipeline, or the API. |

**Creating tests via chat**

```
You: "Create 5 tests for the checkout flow"
→ Analyzes your application structure
→ Creates tests prioritizing revenue-critical paths
→ Shows suggestions for your approval
```

**A change review fills coverage gaps**

```
Pull request detected with untested functionality
→ Creates tests for new features
→ Runs all relevant tests
→ Posts the review with results
```

You don't manage this coordination. It happens from the entry point you use.

## Agents that run a test

The agent that executes a test depends on the application type, the application's default, and any per-test override. See [Agents](/build-tests/agents).


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