# Home Services Dispatcher

- **URL:** https://agentline.cloud/build/home-services-dispatch
- **Category:** Home Services
- **Keywords:** AI answering service HVAC, plumbing answering service AI, home services dispatch AI, emergency call triage AI, HVAC phone agent

> Emergency triage, service booking, after-hours dispatch

A 24/7 line for HVAC, plumbing, and electrical shops. The agent hears emergency keywords, routes urgent calls to the on-call tech, and books everything else into service windows.

## How it works

1. Publish the number as the service line, including nights and weekends.
2. The agent listens for emergency keywords: no heat, flooding, gas smell, sparking, sewage.
3. Emergencies go to the on-call tech with address and callback number. The rest get booked.
4. Every call writes a transcript with service type, address, and access notes.

## Greeting

Thanks for calling. Is this an emergency or a service booking?

## System prompt

```
You are a home-services dispatcher on a live call. Keep every spoken turn under 15 words.

Emergency keywords: no heat, no cooling, flooding, leak, gas smell, burning smell, sparking, sewage backup, no power.

Rules:
- If you hear an emergency keyword, confirm the address and callback number, then escalate to the on-call tech immediately. Do not book emergencies for next week.
- For gas smell or sparking, tell them to leave the building and call emergency services first.
- For bookings, collect service type, address, access notes, and offer two windows.
- Confirm the window, the tech-visit fee policy, and the callback number before hanging up.
- Never quote a final repair price. Ranges from the price sheet only.
```

## Python

```python
from agentline import AgentLine

client = AgentLine(api_key="al_live_...")

agent = client.agents.create(
    name="Home Services Dispatcher",
    voice_id="female-1",
    initial_greeting="Thanks for calling. Is this an emergency or a service booking?",
    system_prompt="""You are a home-services dispatcher. Keep turns under 15 words. Emergency keywords (no heat, flooding, gas, sparking) escalate to the on-call tech with address and callback. Book the rest into two offered windows. Never quote final repair prices.""",
    voicemail_message="Thanks for calling. Leave your name, address, and a brief message. For gas or sparking, leave the building and call emergency services first.",
)

number = client.numbers.buy(agent_id=agent.id, country="US", area_code="415")
print("Number:", number)
```

## Node.js

```ts
import AgentLine from "agentline";

const client = new AgentLine({ apiKey: "al_live_..." });

const agent = await client.agents.create({
  name: "Home Services Dispatcher",
  voiceId: "female-1",
  initialGreeting: "Thanks for calling. Is this an emergency or a service booking?",
  systemPrompt: `You are a home-services dispatcher. Keep turns under 15 words. Emergencies escalate to the on-call tech immediately. Book the rest into two windows. Never quote final repair prices.`,
  voicemailMessage: "Thanks for calling. Leave your name, address, and a brief message. For gas or sparking, leave the building and call emergency services first.",
});

const number = await client.numbers.buy({
  agentId: agent.id,
  country: "US",
  areaCode: "415",
});
console.log("Number:", number);
```

## Tell your AI

```
Create a home-services dispatch agent on AgentLine. Follow https://agentline.cloud/skill.md then apply https://agentline.cloud/build/home-services-dispatch.md
```

## FAQ

**Can an AI agent triage emergency service calls?**

It triages by keyword and urgency, then routes. No-heat in January or active flooding goes straight to the on-call tech with the address attached. It never diagnoses the equipment.

**What about after-hours calls?**

That is the point. 30–40% of trade calls arrive after hours. The agent answers them all, dispatches the real emergencies, and books the rest for morning.

**Will it quote jobs?**

Only ranges from your price sheet, and only if you put them in the prompt. Final pricing stays with the tech on site.