create_agent
Create a new AI agent with configurable language, voice, model, and workflow type. Supports single prompt or multi-agent playbooks.
Instructions
Create a new AI agent in your organization. By default the agent is a single_prompt agent with gpt-4.1 model and daniel voice (waves_lightning_v3_1); set workflow_type to multi_agents for a Playbooks agent (an intent router + specialist SOP playbooks — add them via add_playbooks after creation). The STT transcriber defaults to Pulse — change it (e.g. to pulse-legacy) via update_agent_config after creation. Returns the created agent's ID. For single_prompt agents, set the prompt via update_agent_prompt after creation.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Name for the new agent | |
| language | No | Language configuration. Defaults to English. | |
| slm_model | No | LLM model for the agent. Defaults to gpt-4.1. | |
| description | No | Short description of what the agent does | |
| synthesizer | No | Voice synthesizer configuration | |
| first_message | No | First message the agent says when a call starts (max 500 chars) | |
| global_prompt | No | Global system prompt for the agent (max 4000 chars). For the main prompt, use update_agent_prompt after creation. | |
| workflow_type | No | Agent type. single_prompt (default) = one prompt + tools. multi_agents = Playbooks: an intent router classifies each caller turn and routes to a specialist playbook (SOP) with its own prompt and scoped tools — configure via add_playbooks / configure_playbooks. multi_agents is domain-gated; the API returns 403 if your account isn't allowlisted. | |
| background_sound | No | Background sound during calls | |
| default_variables | No | Default template variables for the agent prompt (e.g. { company_name: 'Acme' }) | |
| knowledge_base_id | No | Knowledge base ID to attach to the agent | |
| smart_turn_config | No | Smart turn detection configuration | |
| allow_inbound_call | No | Whether to allow inbound calls (default true) | |
| enable_style_guide | No | Enable conversational style guide (default true) | |
| allow_interruptions | No | Whether to allow user interruptions (default true) | |
| pronunciation_dicts | No | Custom pronunciation dictionary | |
| voicemail_detection | No | Voicemail detection configuration | |
| wait_for_user_to_speak_first | No | Wait for user to speak before agent starts (default false) |