Docs

Create Chat Agent

Creates a chat agent in Retell AI.

POST

Query

Field selectionChoose which fields should be included in the response. Learn more
string

Comma-separated response fields to include.

Body

Arguments
array of stringrequired

List of PII categories to scrub from transcripts and recordings.

array of string

Examples of the variable value to teach model the style and syntax.

array of string

Selected prohibited user topic categories to check. When user messages contain these topics, the agent will respond with a placeholder message instead of processing the request.

array of string

Selected prohibited agent topic categories to check. When agent messages contain these topics, they will be replaced with a placeholder message.

array of object

Post chat analysis data to extract from the chat. This data will augment the pre-defined variables extracted in the chat analysis. This will be available after the chat ends.

objectrequired
array of string

Which webhook events this agent should receive. If not set, defaults to chat_started, chat_ended, chat_analyzed.

stringrequired

type of the Response Engine. Allowed values: retell-llm.

stringrequired

id of the Retell LLM Response Engine.

number

Version of the Retell LLM Response Engine.

string

The name of the chat agent. Only used for your own reference.

string

Message to display when the chat is automatically closed.

number

If users stay silent for a period after agent speech, end the chat. The minimum value allowed is 120,000 ms (2 minutes). The maximum value allowed is 259,200,000 ms (72 hours). By default, this is set to 3,600,000 (1 hour).

string

Specifies what language (and dialect) the chat will operate in. For instance, selecting `en-GB` optimizes for British English. If unset, will use default value `en-US`. Select `multi` for multilingual support, currently this supports Spanish and English.

string

The webhook for agent to listen to chat events. See what events it would get at [webhook doc](/features/webhook). If set, will binds webhook events for this agent to the specified url, and will ignore the account level webhook for this agent. Set to `null` to remove webhook url from this agent.

number

The timeout for the webhook in milliseconds. If not set, default value of 10000 will apply.

string

Controls what data is stored for this agent. "everything" stores all data including transcripts and recordings. "everything_except_pii" stores data but excludes PII when possible based on PII configuration. "basic_attributes_only" stores only basic metadata. If not set, defaults to "everything". Allowed values: everything, everything_except_pii, basic_attributes_only.

number

Number of days to retain call/chat data before automatic deletion. Must be between 1 and 730 days. If not set, data is retained forever (no automatic deletion).

boolean

Whether this agent opts in to signed url for public log. If not set, default value of false will apply.

number

The expiration time for the signed url in milliseconds. Only applicable when opt_in_signed_url is true. If not set, default value of 86400000 (24 hours) will apply.

stringrequired

Type of the variable to extract. Allowed values: string.

stringrequired

Name of the variable.

stringrequired

Description of the variable.

boolean

Whether this data is required. If true and the data is not extracted, the call will be marked as unsuccessful.

string

Available LLM models for agents.

string

The prompt to use for post call analysis to evaluate whether the call is successful. Set to null to use the default prompt.

string

The prompt to use for post call analysis to summarize the call. Set to null to use the default prompt.

string

Prompt to guide how the post chat analysis should evaluate user sentiment. When unset, the default system prompt is used. Set to null to use the default prompt.

object
stringrequired

The processing mode for PII scrubbing. Currently only post-call is supported. Allowed values: post_call.

object
boolean

Whether the agent is public. When set to true, the agent is available for public agent preview link.

Every app you connect,one REST pattern

Call any app with one REST pattern. MindCloud handles each provider's auth, request shape, and responses for you.

Learn what the Universal API is
One REST patternUse the same request structure across apps like Slack, HubSpot, Salesforce, and thousands more.
Managed connectionsSend a MindCloud connection ID instead of handling provider tokens, refresh logic, and credential storage yourself.
Action-level docsEach action page shows the exact endpoint, required arguments, optional controls, and response behavior for that app version.