# Scheduling Agent

- **URL:** https://agentline.cloud/build/scheduling-agent
- **Category:** Productivity
- **Keywords:** AI scheduling agent, book meetings by phone AI, AI appointment booking, phone number for AI agents, voice scheduling agent

> Call your agent to book time — it knows your rules

A voice scheduling agent that answers inbound calls, proposes times from your rules, and confirms the booking out loud. Same pattern as an email scheduling inbox, on a real phone number.

## How it works

1. Provision a US or Canadian number on AgentLine and attach this prompt.
2. Callers reach the agent inbound. It asks what they need and which windows work.
3. The agent only offers times that match your rules (weekdays, buffers, duration).
4. It reads the booking back, confirms, and logs the transcript for your calendar step.

## Greeting

Hi, this is the scheduling desk. What are we booking?

## System prompt

```
You are a scheduling agent on a live phone call. Keep every spoken turn under 15 words.

Rules:
- Only offer weekdays 10:00–16:00 America/Los_Angeles.
- Default meetings are 30 minutes with a 10-minute buffer.
- Never double-book. If a slot is taken, offer the next two open times.
- Confirm name, phone, and purpose before locking a time.
- If the caller wants something you cannot book, say so and offer a human follow-up.
- Do not discuss other topics. Stay on scheduling.
```

## Python

```python
from agentline import AgentLine

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

agent = client.agents.create(
    name="Scheduling Agent",
    voice_id="female-1",
    initial_greeting="Hi, this is the scheduling desk. What are we booking?",
    system_prompt="""You are a scheduling agent on a live phone call. Keep every spoken turn under 15 words.
Only offer weekdays 10:00-16:00 America/Los_Angeles. Default 30 minutes with a 10-minute buffer.
Confirm name, phone, and purpose before locking a time.""",
)

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

## Node.js

```ts
import AgentLine from "agentline";

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

const agent = await client.agents.create({
  name: "Scheduling Agent",
  voiceId: "female-1",
  initialGreeting: "Hi, this is the scheduling desk. What are we booking?",
  systemPrompt: `You are a scheduling agent on a live phone call. Keep every spoken turn under 15 words.
Only offer weekdays 10:00-16:00 America/Los_Angeles. Default 30 minutes with a 10-minute buffer.`,
});

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

## Tell your AI

```
Create a scheduling voice agent on AgentLine. Follow https://agentline.cloud/skill.md then apply the prompt from https://agentline.cloud/build/scheduling-agent.md
```

## FAQ

**Can an AI agent book meetings over the phone?**

Yes. Give the agent a real AgentLine number, set a scheduling prompt with your hours and duration rules, and callers book by voice. The transcript is the record you push into a calendar.

**Does this work with OpenClaw or Hermes?**

Yes. Install the AgentLine skill, provision a number, and paste the scheduling prompt. The same template works with OpenClaw, Hermes Agent, Claude Code, Codex, or any LLM that can call the API.

**How is this different from an email scheduling agent?**

Same job, different channel. Email agents wait on threads. This agent answers a phone number in real time, confirms the slot out loud, and stores the call transcript.