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

# Behavior

> Set and edit your agent's global rules, model, personality, and fixed greeting line.

Configure your agent's greeting, personality, model, and rules in **Behavior > General**.

<img src="https://mintcdn.com/polyai/mC-hBNxhbQLRsMMg/images/agent-settings/agent-overview.png?fit=max&auto=format&n=mC-hBNxhbQLRsMMg&q=85&s=28c0bceed01dce2c68652233f9371480" alt="Behavior > General overview" data-og-width="3018" width="3018" data-og-height="1634" height="1634" data-path="images/agent-settings/agent-overview.png" data-optimize="true" data-opv="3" srcset="https://mintcdn.com/polyai/mC-hBNxhbQLRsMMg/images/agent-settings/agent-overview.png?w=280&fit=max&auto=format&n=mC-hBNxhbQLRsMMg&q=85&s=4283512496e05bc5aab85a548c003971 280w, https://mintcdn.com/polyai/mC-hBNxhbQLRsMMg/images/agent-settings/agent-overview.png?w=560&fit=max&auto=format&n=mC-hBNxhbQLRsMMg&q=85&s=3c872f56d6711e0396ae129d07415a1d 560w, https://mintcdn.com/polyai/mC-hBNxhbQLRsMMg/images/agent-settings/agent-overview.png?w=840&fit=max&auto=format&n=mC-hBNxhbQLRsMMg&q=85&s=7d4057e0fd43c065b580dae525bccd19 840w, https://mintcdn.com/polyai/mC-hBNxhbQLRsMMg/images/agent-settings/agent-overview.png?w=1100&fit=max&auto=format&n=mC-hBNxhbQLRsMMg&q=85&s=2f49ea257013f52ff6a5f3778485b323 1100w, https://mintcdn.com/polyai/mC-hBNxhbQLRsMMg/images/agent-settings/agent-overview.png?w=1650&fit=max&auto=format&n=mC-hBNxhbQLRsMMg&q=85&s=b47ab333ad792c3eb8fcc488a4dd07b8 1650w, https://mintcdn.com/polyai/mC-hBNxhbQLRsMMg/images/agent-settings/agent-overview.png?w=2500&fit=max&auto=format&n=mC-hBNxhbQLRsMMg&q=85&s=1d99070dbbb52fa1b5ff8e396436d698 2500w" />

## When to configure each setting

| Setting                                             | When to use                                                                       | Impact                                                                                                  |
| --------------------------------------------------- | --------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
| **[Agent](/behavior/general/agent)**                | For the initial setup or when rebranding                                          | Personality (tone) and role. The greeting is configured per-channel under **Voice/Chat configuration**. |
| **[Model](/behavior/models/model-use)**             | New agent setup, or optimizing for cost/latency/quality                           | LLM selection. [Raven](/behavior/models/raven) recommended, but other models are also available.        |
| **[Behavior](/behavior/general/rules)**             | Consistent terminology, compliance, edge-case handling                            | Add your global constraints – tone, language style, compliance guardrails, pronunciation overrides.     |
| **[Guardrails](/behavior/guardrails/introduction)** | Safety protections against jailbreaks, hallucination, crisis escalation, and more | Toggle the five built-in platform guardrails. Lives under **Behavior > Guardrails**.                    |

## Configuration sections

<CardGroup cols={2}>
  <Card title="Agent" icon="user" href="/behavior/general/agent">
    Personality and role.
  </Card>

  <Card title="Model" icon="brain" href="/behavior/models/model-use">
    Raven (recommended), OpenAI, Amazon Bedrock, or your own endpoint.
  </Card>

  <Card title="Behavior" icon="list-check" href="/behavior/general/rules">
    Language style, compliance, edge cases, and pronunciation overrides.
  </Card>

  <Card title="Guardrails" icon="shield" href="/behavior/guardrails/introduction">
    Built-in platform protections against jailbreaks, hallucination, and crisis events.
  </Card>

  <Card title="Language" icon="language" href="/behavior/language/multilingual">
    Multilingual settings, language coverage, and translation overrides.
  </Card>
</CardGroup>

## Automate with the Agents API

If you spin up new agents from a reference template — for example, one agent per client or market — you can create and duplicate them from code.

<AccordionGroup>
  <Accordion title="Script agent creation via the Agents API" icon="code">
    The [Agents API](/api-reference/agents/introduction) has endpoints for [creating](/api-reference/agents/endpoint/agents/create-agent) and [duplicating](/api-reference/agents/endpoint/agents/duplicate-agent) agents.

    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    # Create a new agent from scratch
    curl -X POST https://api.us.poly.ai/v1/agents \
      -H "x-api-key: $POLYAI_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{ "name": "Support Agent", "description": "Tier 1 support, US" }'

    # Duplicate an existing agent as a starting point
    curl -X POST https://api.us.poly.ai/v1/agents/AGENT_ID/duplicate \
      -H "x-api-key: $POLYAI_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{ "name": "Support Agent - UK" }'
    ```
  </Accordion>
</AccordionGroup>

## Related pages

<CardGroup cols={2}>
  <Card title="Agents endpoints" icon="square-terminal" href="/api-reference/agents/endpoint/agents/create-agent">
    Create, duplicate, and configure agents from code.
  </Card>

  <Card title="Deployment pipeline" icon="server" href="/environments-and-versions/introduction">
    Publish and promote versions through Sandbox, Pre-release, and Live.
  </Card>
</CardGroup>
