ai
Start an AI agent session on the call. The AI agent handles the conversation
using the provided prompt, tools, and configuration. Returns an
AIAction that you can use to stop
the AI session or wait for it to complete.
For building AI agents with the full framework (prompts, tools, skills, contexts),
use AgentBase. The ai() method
is for lower-level RELAY control where you configure the AI inline.
See also amazonBedrock() for using Amazon Bedrock as the LLM backend.
This method executes the SWML ai verb on the call. See the
SWML AI reference for the full specification of all supported
parameters and behaviors.
Parameters
controlId
Custom control ID. Auto-generated if not provided.
agent
Fabric agent resource ID. When set, the AI uses a pre-configured agent from SignalWire Fabric instead of inline configuration.
prompt
The main prompt configuration.
prompt.text
The system prompt text that defines the AI agent’s behavior.
prompt.temperature
LLM temperature for the main prompt.
prompt.top_p
LLM top_p sampling parameter.
postPrompt
Post-prompt configuration for summarization or analysis after the conversation ends.
postPrompt.text
The post-prompt text.
postPromptUrl
URL to receive the post-prompt result via webhook.
postPromptAuthUser
Username for basic auth on the post-prompt webhook.
postPromptAuthPassword
Password for basic auth on the post-prompt webhook.
globalData
Data accessible to the AI agent and SWAIG functions throughout the session.
pronounce
Pronunciation rules for words or phrases the TTS engine should handle specially.
hints
Speech recognition hints to improve accuracy for domain-specific terms.
languages
Language configurations for multilingual support.
SWAIG
SWAIG (SignalWire AI Gateway) configuration for tool/function definitions.
aiParams
Additional AI parameters such as barge_confidence, end_of_speech_timeout,
attention_timeout, and other LLM tuning settings.
onCompleted
Callback invoked when the AI session ends.
Returns
Promise<AIAction> — An action handle with stop() and wait() methods.