> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://poly-ai.ferndocs.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://poly-ai.ferndocs.com/_mcp/server.

# 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**.

![Behavior > General overview](/_fern-files/_img/724b4c10b1d6640cd4dfbddaac166c23ead32c4aab26e2ccadc069b76f51c483.webp)

## When to configure each setting

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

## Configuration sections

#### [Agent](/agent-studio/behavior/general/personality-and-role)

Personality and role.

#### [Model](/agent-studio/behavior/models/overview)

Raven (recommended), OpenAI, Amazon Bedrock, or your own endpoint.

#### [Behavior](/agent-studio/behavior/general/behavior)

Language style, compliance, edge cases, and pronunciation overrides.

#### [Guardrails](/agent-studio/behavior/guardrails/guardrails)

Built-in platform protections against jailbreaks, hallucination, and crisis events.

#### [Language](/agent-studio/behavior/language/multi-language)

Multilingual settings, language coverage, and translation overrides.

## 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.

#### Script agent creation via the Agents API

The [Agents API](/api-reference/build-deploy/agents-api/overview) has endpoints for [creating](/api-reference/api-reference/agents/create) and [duplicating](/api-reference/api-reference/agents/duplicate) agents.

```bash
# 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" }'
```

## Related pages

#### [Agents endpoints](/api-reference/api-reference/agents/create)

Create, duplicate, and configure agents from code.

#### [Deployment pipeline](/agent-studio/deployments/overview)

Publish and promote versions through Sandbox, Pre-release, and Live.