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

# Introduction

> Multilingual voice agents and a practical integration model for consumer brands

MrAssistant AI helps teams ship **multilingual voice and agent** experiences for **business-to-consumer** use cases: self-serve help, guided flows, and handoffs to human teams when needed.

These docs stay **high level**: how the product fits together, what to plan for on the voice side, and why many B2C teams adopt an **MCP-style integration layer** so assistants stay maintainable as you add channels and capabilities.

## Get started

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    A simple mental model for going from idea to integrated experience.
  </Card>

  <Card title="MCP for B2C" icon="plug" href="/get-started/mcp-for-b2c">
    Why a Model Context Protocol server matters for consumer-facing AI at scale.
  </Card>

  <Card title="Web and voice" icon="microphone" href="/get-started/web-and-voice">
    How web, mobile, and realtime voice pieces fit together.
  </Card>

  <Card title="API reference" icon="code" href="/api-reference/introduction">
    Technical reference generated from the public API description.
  </Card>
</CardGroup>

## Build

<CardGroup cols={2}>
  <Card title="Agents" icon="robot" href="/agents/overview">
    What an agent represents and how you evolve it over time.
  </Card>

  <Card title="Knowledge and tools" icon="books" href="/agents/knowledge-and-tools">
    Grounding content and extending behavior with controlled actions.
  </Card>

  <Card title="Voice and providers" icon="waveform" href="/voice/providers">
    Speech, language models, and provider choice at a glance.
  </Card>

  <Card title="Multilingual" icon="language" href="/voice/multilingual">
    Serving more than one language and locale with confidence.
  </Card>
</CardGroup>

For machine-readable API details, your team can use the published **OpenAPI** document linked from the site header when that fits your workflow.