Implementation:Elevenlabs Elevenlabs python PromptAgentApiModelWorkflowOverrideOutput
| Field | Value |
|---|---|
| source | Elevenlabs_Elevenlabs_python |
| domains | Conversational AI, Agent Configuration, LLM, Workflow Override |
| last_updated | 2026-02-15 |
Overview
Description
PromptAgentApiModelWorkflowOverrideOutput is a Pydantic model representing the output schema for workflow-level overrides of the prompt agent configuration in the ElevenLabs API. It provides extensive control over the LLM-powered agent, including prompt customization, LLM selection, reasoning effort, temperature, token limits, tool configuration, knowledge bases, RAG settings, and backup LLM cascading. This model is auto-generated by Fern from the ElevenLabs API definition and extends UncheckedBaseModel.
Usage
This model is returned by the ElevenLabs API when retrieving agent workflow override configurations. It is used to inspect or pass along overrides that control how the conversational agent's prompt, LLM backend, tools, and knowledge bases are configured at the workflow level.
Code Reference
Source Location
src/elevenlabs/types/prompt_agent_api_model_workflow_override_output.py
Class Signature
class PromptAgentApiModelWorkflowOverrideOutput(UncheckedBaseModel):
...
Import Statement
from elevenlabs.types import PromptAgentApiModelWorkflowOverrideOutput
I/O Contract
| Field | Type | Required | Description |
|---|---|---|---|
| prompt | Optional[str] |
No | The prompt for the agent. |
| llm | Optional[Llm] |
No | The LLM to query with the prompt and the chat history. If using data residency, the LLM must be supported in the data residency environment. |
| reasoning_effort | Optional[LlmReasoningEffort] |
No | Reasoning effort of the model. Only available for some models. |
| thinking_budget | Optional[int] |
No | Max number of tokens used for thinking. Use 0 to turn off if supported by the model. |
| temperature | Optional[float] |
No | The temperature for the LLM. |
| max_tokens | Optional[int] |
No | If greater than 0, maximum number of tokens the LLM can predict. |
| tool_ids | Optional[List[str]] |
No | A list of IDs of tools used by the agent. |
| built_in_tools | Optional[BuiltInToolsWorkflowOverrideOutput] |
No | Built-in system tools to be used by the agent. |
| mcp_server_ids | Optional[List[str]] |
No | A list of MCP server ids to be used by the agent. |
| native_mcp_server_ids | Optional[List[str]] |
No | A list of Native MCP server ids to be used by the agent. |
| knowledge_base | Optional[List[KnowledgeBaseLocator]] |
No | A list of knowledge bases to be used by the agent. |
| custom_llm | Optional[CustomLlm] |
No | Definition for a custom LLM if LLM field is set to 'CUSTOM_LLM'. |
| ignore_default_personality | Optional[bool] |
No | Whether to remove the default personality lines from the system prompt. |
| rag | Optional[RagConfigWorkflowOverride] |
No | Configuration for RAG. |
| timezone | Optional[str] |
No | Timezone for displaying current time in system prompt (e.g., 'America/New_York', 'Europe/London', 'UTC'). |
| backup_llm_config | Optional[PromptAgentApiModelWorkflowOverrideOutputBackupLlmConfig] |
No | Configuration for backup LLM cascading. Can be disabled, use system defaults, or specify custom order. |
| cascade_timeout_seconds | Optional[float] |
No | Time in seconds before cascading to backup LLM. Must be between 2 and 15 seconds. |
| tools | Optional[List[PromptAgentApiModelWorkflowOverrideOutputToolsItem]] |
No | A list of tools that the agent can use over the course of the conversation (use tool_ids instead). |
Usage Examples
from elevenlabs.types import PromptAgentApiModelWorkflowOverrideOutput
# Typically received as part of an API response
agent_override = PromptAgentApiModelWorkflowOverrideOutput(
prompt="You are a helpful customer service agent.",
temperature=0.7,
max_tokens=1024,
tool_ids=["tool_abc123", "tool_def456"],
timezone="America/New_York",
)