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

# Phone Support Agent

> Build voice agents that answer phone calls with RAG-powered knowledge retrieval

<Card title="View Phone & RAG Example on GitHub" icon="github" href="https://github.com/GetStream/vision-agents/tree/main/examples/03_phone_and_rag_example">
  Check out the complete Phone & RAG example in our GitHub repository
</Card>

In this example, we build both inbound and outbound calling agents using [Twilio](https://www.twilio.com/) for the phone network, [Stream](https://getstream.io/) for edge transport, and RAG backends ([Gemini FileSearch](https://ai.google.dev/gemini-api/docs/file-search) or [Turbopuffer](https://turbopuffer.com/)) for knowledge retrieval. The inbound agent answers calls and uses a knowledge base to provide product information. The outbound agent makes calls programmatically — like booking a restaurant reservation.

<Info>
  Vision Agents requires a [Stream](https://getstream.io/try-for-free/) account
  for real-time transport. Most providers offer free tiers to get started.
</Info>

## What You Will Build

* Answer inbound phone calls with an AI agent powered by [Twilio](https://www.twilio.com/) voice
* Make outbound calls programmatically for tasks like booking reservations
* Retrieve real-time knowledge using [Gemini FileSearch](https://ai.google.dev/gemini-api/docs/file-search) or [Turbopuffer](https://turbopuffer.com/) RAG
* Handle bi-directional audio via Twilio media streams over WebSocket
* Run on [Stream's](https://getstream.io/) low-latency edge network

## Next Steps

<CardGroup cols={2}>
  <Card title="RAG Guide" icon="book" href="/guides/rag">
    Learn more about RAG backends and knowledge retrieval
  </Card>

  <Card title="HTTP Server Guide" icon="server" href="/guides/http-server">
    Deploy your phone bot with the built-in HTTP server
  </Card>
</CardGroup>