> ## Documentation Index
> Fetch the complete documentation index at: https://developers.callaro.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Agents and Adaptive Scripting

> See how Callaro agents combine voice, intent handling, and controlled branching to keep conversations on policy.

# Agents are where business policy meets voice execution.

An agent in Callaro bundles the voice, script logic, objection handling, retrieval permissions, tool access, and response style that should govern a conversation.

<CardGroup cols={2}>
  <Card title="Human answer" icon="user-check">The agent moves into discovery, qualification, objection handling, and next-step capture.</Card>
  <Card title="Voicemail" icon="voicemail">The agent follows a different branch, keeping the message concise and aligned with campaign policy.</Card>
</CardGroup>

## Prompt and policy guardrails

* Keep one primary objective per agent (for example qualify + book).
* Define explicit objection boundaries and escalation behavior.
* Restrict tool access to only required CRM/calendar actions.
* Review transcript samples weekly and tune branch logic iteratively.

## Anti-patterns to avoid

| Anti-pattern                  | Why it hurts                                |
| ----------------------------- | ------------------------------------------- |
| One script for every campaign | Low relevance and weaker conversion quality |
| Broad tool permissions        | Increased risk of incorrect external writes |
| No voicemail-specific branch  | Inconsistent outcomes for unanswered calls  |

<Note>
  The highest-performing agents usually have narrower objectives than teams expect at first. A script designed to qualify and book a meeting will outperform one that also tries to educate, negotiate, and close in a single call.
</Note>