ai

Create an AI agent with a prompt. Since the text prompt is central to getting great results out of the AI, it is highly recommended that you also read the Prompting Best Practices guide.

Parameters

The only required parameter is prompt. But the others are quite powerful, so we recommend trying them out!

Name	Type	Description
prompt	object	Establishes the initial set of instructions and settings to configure the agent. This is a required parameter.
post_prompt	object	The final set of instructions and configuration settings to send to the agent.
post_prompt_url	string	The URL to which to send status callbacks and reports.
post_prompt_auth_user	string	Auth username for post_url endpoint.
post_prompt_auth_password	string	Auth password for post_url endpoint.
params	object	A JSON object containing parameters as key-value pairs.
SWAIG	object	An array of JSON objects to create user-defined functions/endpoints that can be executed during the dialogue.
hints	string	An array of hints (as strings) to provide context to the dialogue.
languages	object	An array of JSON objects defining supported languages in the conversation.
pronounce	object	An array of JSON objects to clarify the AI's pronunciation of words or expressions.
verbose_logs	boolean	Enable verbose logging.
hold_music	string	A URL for the hold music to play, accepting WAV, mp3, and FreeSWITCH tone_stream.
hold_on_process	boolean	Enables hold music during SWAIG processing.
debug_webhook_url	string	Each interaction between the AI and end user is posted in real time to the established URL.
debug_webhook_level	boolean	Enables debugging to the set URL. If a URL is set, this param defaults to 1.
acknowledge_interruptions	boolean or string	Instructs the agent to acknowledge crosstalk and confirm user input when the user speaks over the agent.
interrupt_prompt	string	Provide a prompt for the agent to handle crosstalk.
interrupt_on_noise	boolean	When enabled, barges agent upon any sound interruption longer than 1 second.
input_poll_freq	string	Check for input function with check_for_input. Example use case: Feeding an inbound SMS to AI on a voice call, eg., for collecting an email address or other complex information.
ai_volume	string	Set the AI volume with numerical values between -50 and +50.
barge_match_string	string	Takes a string, including a regular expression, defining barge behavior. For example, this param can direct the AI to stop when the word "hippopotomus" is input.
barge_min_words	string	Defines the number of words that must be input before triggering barge behavior, in a range of 1-99.
swaig_allow_swml	boolean	Allows your SWAIG to return SWML to be executed.
swaig_allow_settings	boolean	Allows tweaking any of the indicated settings, such as barge_match_string, using the returned SWML from the SWAIG function.
swaig_post_conversation	boolean	Post entire conversation to any SWAIG call.
conversation_id	string	Used by check_for_input and save_conversation to identify an individual conversation.
transfer_summary	boolean	Pass a summary of a conversation from one AI agent to another. For example, transfer a call summary between support agents in two departments.
save_conversation	boolean	Performs an additional call to save the current conversation summary by conversation ID. Use this param to preserve conversation context between calls.
local_tz	string	Takes a time zone string. For example: UTC+5, America/New_York, or any other convention defined by the International Bureau of Weights and Measures (BIPM).
background_file	string	Defines a file via URL to play background noise.
background_file_loops	boolean	Sets background_file behavior to loop if true.
background_file_volume	string	Defines background_file volume within a range of -50 to +50.
digit_timeout	string	Sets time duration to wait for DTMF before timing out, in a range from 1 to 30000 milliseconds.
digit_terminators	string	Sets a digit, such as a pound (#) sign, to terminate input. Fun fact: The pound sign is also known as an "octothorp."
end_of_speech_timeout	string	Sets a time duration for the agent to wait after speech before timing out, in a range between 250 to 10000 milliseconds.
energy_level	string	Sets voice detection threshold for user speech, in a range from 0 to 100 dB.
attention_timeout	string	Sets a time duration for the user to respond to the AI agent before timeout, in a range from 10000 to 600000, or 0 milliseconds.
inactivity_timeout	string	Sets a time duration for the user to speak before timeout, in a range from 10000 to 3600000.
outbound_attention_timeout	string	Sets a time duration for the outbound call recipient to respond to the AI agent before timeout, in a range from 10000 to 600000.
languages_enabled	boolean	Allows multilingualism when true.
conscience	string	Sets the prompt which binds the agent to its purpose.
agent_meta_data	object	A powerful and flexible environmental variable which can accept arbitrary data. All contained information can be accessed and expanded within the prompt - for example, by using a template string.