# GTM Agent

- **URL:** https://agentline.cloud/build/gtm-agent
- **Category:** Outbound
- **Keywords:** AI GTM agent, AI outbound sales calls, agentic calling, AI lead follow-up, voice infrastructure for AI

> Personalized outbound calls, reply classification, warm-ack + handoff

A go-to-market voice agent that dials new leads, classifies the reply, and hands warm conversations to a human. Built for the five-minute follow-up window.

## How it works

1. Create the agent with this prompt and buy a number.
2. POST /v1/calls for each new lead within minutes of signup.
3. The agent introduces itself, qualifies interest, and never pitches past a no.
4. Warm replies get a booked callback. Cold or DNC replies end the call cleanly.

## Greeting

Hi, this is Alex from the team. Did I catch you at a bad time?

## Voicemail

Hi, this is Alex from the team. I was following up on your signup. Call me back on this number or I'll try you again tomorrow.

## System prompt

```
You are an outbound GTM agent on a live call. Keep every spoken turn under 12 words.

Goal: confirm they signed up, learn if they want help, book a human callback if yes.

Rules:
- Identify yourself and the company in the first turn.
- Ask one question at a time.
- If they are busy, offer a callback window and hang up politely.
- If they are not interested, thank them and end the call. Never argue.
- If they are interested, collect name, role, and a time for a human.
- Do not quote prices. Do not improvise discounts.
- If you reach voicemail, stop. AgentLine leaves the configured voicemail_message.
```

## Python

```python
from agentline import AgentLine

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

agent = client.agents.create(
    name="GTM Agent",
    voice_id="male-1",
    initial_greeting="Hi, this is Alex from the team. Did I catch you at a bad time?",
    voicemail_message="Hi, this is Alex from the team. I was following up on your signup. Call me back on this number.",
    system_prompt="""You are an outbound GTM agent. Keep turns under 12 words.
Identify yourself, qualify interest, book a human callback if they say yes.
Never argue with a no. Never quote prices.""",
)

number = client.numbers.buy(agent_id=agent.id, country="US", area_code="415")
call = client.calls.create(agent_id=agent.id, to="+14155557890")
print(call)
```

## Node.js

```ts
import AgentLine from "agentline";

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

const agent = await client.agents.create({
  name: "GTM Agent",
  voiceId: "male-1",
  initialGreeting: "Hi, this is Alex from the team. Did I catch you at a bad time?",
  voicemailMessage: "Hi, this is Alex from the team. I was following up on your signup.",
  systemPrompt: `You are an outbound GTM agent. Keep turns under 12 words.
Qualify interest and book a human callback if they say yes.`,
});

await client.numbers.buy({ agentId: agent.id, country: "US", areaCode: "415" });
const call = await client.calls.create({ agentId: agent.id, to: "+14155557890" });
console.log(call);
```

## Tell your AI

```
Create a GTM outbound calling agent on AgentLine. Follow https://agentline.cloud/skill.md then apply https://agentline.cloud/build/gtm-agent.md
```

## FAQ

**Can an AI agent make outbound sales calls?**

Yes. AgentLine provisions a real number and dials via POST /v1/calls. The agent reads the live transcript and replies with text; the telephony layer speaks it.

**What happens if the lead does not pick up?**

Set voicemail_message on the agent. AgentLine detects the mailbox and leaves that message. Without it, the agent hangs up instead of improvising.

**How fast should the agent call a new lead?**

Teams using this template dial within 60 seconds of signup. Leads contacted in five minutes convert several times faster than leads contacted an hour later.
