# Swap the Telephony. Keep Your Stack.

Whether you use Vapi, Retell, or another AI orchestration layer, the telephony underneath it is the bottleneck: latency, cost, and a vendor pivoting away from phones.

< 1.2s

typical AI response latency

2,000+

companies in production

5–10

business days for number porting

0

changes to your AI layer

## Why Swap

### The Telephony Layer Is the Bottleneck

#### Your telephony provider is pivoting to AI

Legacy providers are deprioritizing phone infrastructure to chase AI revenue. The layer underneath your AI is getting less attention, not more.

#### Every network hop adds latency

Audio travels through a carrier, telephony provider, and AI layer. SignalWire is built for real-time media with fewer hops.

#### Markup stacks through the vendor chain

Your provider marks up carrier rates, and the orchestration layer marks up the provider. You pay margins on margins.

#### When the call drops, who owns it?

Debugging across telephony and AI orchestration logs at 2am is the hidden cost of a multi-vendor stack.

## Build a Voice AI Agent

### Languages Supported
- Python
- TypeScript
- Go
- Java
- Ruby
- PHP
- Perl
- C++
- C#

```python
from signalwire import AgentBase
from signalwire.core.function_result import FunctionResult

class SupportAgent(AgentBase):
    def __init__(self):
        super().__init__(name="Support Agent", route="/support")
        self.prompt_add_section("Instructions", body="You are a customer support agent. "
            "Greet the caller and resolve their issue.")
        self.add_language("English", "en-US", "rime.spore:mistv2")

@AgentBase.tool(name="check_order")
    def check_order(self, order_id: str):
        """Check the status of a customer order. """
        return FunctionResult(f"Order {order_id}: shipped, ETA April 2nd")

agent = SupportAgent()
agent.run()
```

## What Changes, What Stays

### Before: Legacy Telephony

- Separate telephony, STT, TTS, and LLM providers, each with its own SDK
- Your glue code manages state across all four services
- Each vendor adds a separate queue, invoice, and escalation path
- Compliance and observability must be rebuilt across every vendor
- 16 to 23 months before a production call

### After: SignalWire Telephony

- Telephony, STT, TTS, and LLM in one platform
- AI runs inside the media stack, not outside it
- 800–1200ms typical response latency
- One vendor, one invoice, one escalation path
- Production calls in four to six weeks
- State management is platform-native

## From Install to Production

### Day 1: Install and build your first agent

Install signalwire-agents, define your agent class, add a prompt, and make your first phone call to a working AI agent.

### Weeks 1–2: Connect your business logic

Add tool functions that call your backend: order lookups, appointment scheduling, account verification, and the tools that differentiate your product.

### Weeks 2–3: Structure conversation flow

Define steps with scoped prompts and scoped tools. Each step handles one phase of the conversation with focused context.

### Weeks 4–6: Go live

Deploy your agent as a standard HTTP microservice. Provision phone numbers, route calls, and move into production.

### Weeks 3–4: Test and iterate

Test with real calls. Iterate on prompts and flows. Use the sandbox environment for rapid development cycles.

## Sigmond Runs on SignalWire

A voice and video AI agent built on the SignalWire SDK, wired to a live knowledge base, able to see what you show him. Build the same thing on voice, phone, WhatsApp, or SIP, or an entire white-label platform with SignalWire as the network underneath.

## Call recording

This call is recorded. Audio and transcripts are used to improve our AI and
customer support experience, and aren't shared or sold to third parties.

## Swap the telephony layer. Keep everything else.

Provision SignalWire numbers and configure SIP trunking. Your AI agents keep running without changes.