Agent

A Dialogflow agent is a virtual agent that handles conversations with your end-users. It is a natural language understanding module that understands the nuances of human language. Dialogflow translates end-user text or audio during a conversation to structured data that your apps and services can understand. You design and build a Dialogflow agent to handle the types of conversations required for your system.

For more information about agents, see the Agent guide.

JSON representation
{
  "parent": string,
  "displayName": string,
  "defaultLanguageCode": string,
  "supportedLanguageCodes": [
    string
  ],
  "timeZone": string,
  "description": string,
  "avatarUri": string,
  "enableLogging": boolean,
  "matchMode": enum (MatchMode),
  "classificationThreshold": number,
  "apiVersion": enum (ApiVersion),
  "tier": enum (Tier)
}
Fields
parent

string

Required. The project of this agent. Format: projects/<Project ID> or projects/<Project ID>/locations/<Location ID>

displayName

string

Required. The name of this agent.

defaultLanguageCode

string

Required. The default language of the agent as a language tag. See Language Support for a list of the currently supported language codes. This field cannot be set by the Update method.

supportedLanguageCodes[]

string

Optional. The list of all languages supported by this agent (except for the defaultLanguageCode).

timeZone

string

Required. The time zone of this agent from the time zone database, e.g., America/New_York, Europe/Paris.

description

string

Optional. The description of this agent. The maximum length is 500 characters. If exceeded, the request is rejected.

avatarUri

string

Optional. The URI of the agent's avatar. Avatars are used throughout the Dialogflow console and in the self-hosted Web Demo integration.

enableLogging

boolean

Optional. Determines whether this agent should log conversation queries.

matchMode
(deprecated)

enum (MatchMode)

Optional. Determines how intents are detected from user queries.

classificationThreshold

number

Optional. To filter out false positive results and still get variety in matched natural language inputs for your agent, you can tune the machine learning classification threshold. If the returned score value is less than the threshold value, then a fallback intent will be triggered or, if there are no fallback intents defined, no intent will be triggered. The score values range from 0.0 (completely uncertain) to 1.0 (completely certain). If set to 0.0, the default of 0.3 is used.

apiVersion

enum (ApiVersion)

Optional. API version displayed in Dialogflow console. If not specified, V2 API is assumed. Clients are free to query different service endpoints for different API versions. However, bots connectors and webhook calls will follow the specified API version.

tier

enum (Tier)

Optional. The agent tier. If not specified, TIER_STANDARD is assumed.

MatchMode

Match mode determines how intents are detected from user queries.

Enums
MATCH_MODE_UNSPECIFIED Not specified.
MATCH_MODE_HYBRID Best for agents with a small number of examples in intents and/or wide use of templates syntax and composite entities.
MATCH_MODE_ML_ONLY Can be used for agents with a large number of examples in intents, especially the ones using @sys.any or very large custom entities.

ApiVersion

API version for the agent.

Enums
API_VERSION_UNSPECIFIED Not specified.
API_VERSION_V1 Legacy V1 API.
API_VERSION_V2 V2 API.
API_VERSION_V2_BETA_1 V2beta1 API.

Tier

Represents the agent tier.

Enums
TIER_UNSPECIFIED Not specified. This value should never be used.
TIER_STANDARD Trial Edition, previously known as Standard Edition.
TIER_ENTERPRISE Essentials Edition, previously known as Enterprise Essential Edition.
TIER_ENTERPRISE_PLUS

Essentials Edition (same as TIER_ENTERPRISE), previously known as Enterprise Plus Edition.