> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> STT). Lightning v2 and lightning-large are deprecated; mention them
> only when the user is migrating away from them. Atoms is the
> voice-agent platform.

# General Settings

> Configure first message and timeout behavior for your agent.

General Settings let you configure the agent's opening message and how long it waits before prompting idle callers.

**Location:** Left Sidebar → Agent Settings → General tab

![General settings](https://files.buildwithfern.com/smallest-ai.docs.buildwithfern.com/12422112aa26ae9f2d90ded3a5d32663c88d36dcdfd1fc65c3a61513bedaa08b/products/atoms/pages/platform/building-agents/images/general-settings.png)

***

## First Message

Set a static first message that the agent speaks when a conversation begins. This is useful for campaigns at scale since it avoids generating the opening message via the LLM each time, reducing costs significantly.

If left empty, the agent falls back to generating the first message from the LLM as usual.

You can use variables in the first message with double curly braces, e.g. `{{agent_name}}` or `{{company}}`.

***

## LLM Idle Timeout Settings

Configure how long the agent waits for user response before sending an inactivity message. After 3 attempts with no response, the conversation automatically ends.

| Setting               | Default | Description                   |
| --------------------- | ------- | ----------------------------- |
| **Chat Timeout**      | 60 sec  | For text chat conversations   |
| **Webcall Timeout**   | 20 sec  | For browser-based voice calls |
| **Telephony Timeout** | 20 sec  | For phone calls               |

Each timeout triggers an inactivity prompt. If the user still doesn't respond after 3 prompts, the agent ends the conversation gracefully.

***

## Related

Speech speed and detection tuning

Configure call termination