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.

To get more information about Agent, see:

API documentation
How-to Guides
- Official Documentation

Create a Agent Resource

new Agent(name: string, args: AgentArgs, opts?: CustomResourceOptions);

def Agent(resource_name, opts=None, api_version=None, avatar_uri=None, classification_threshold=None, default_language_code=None, description=None, display_name=None, enable_logging=None, match_mode=None, project=None, supported_language_codes=None, tier=None, time_zone=None, __props__=None);

func NewAgent(ctx *Context, name string, args AgentArgs, opts ...ResourceOption) (*Agent, error)

public Agent(string name, AgentArgs args, CustomResourceOptions? opts = null)

name string: The unique name of the resource.
args AgentArgs: The arguments to resource properties.
opts CustomResourceOptions: Bag of options to control resource's behavior.

resource_name str: The unique name of the resource.
opts ResourceOptions: A bag of options that control this resource's behavior.

ctx Context: Context object for the current deployment.
name string: The unique name of the resource.
args AgentArgs: The arguments to resource properties.
opts ResourceOption: Bag of options to control resource's behavior.

name string: The unique name of the resource.
args AgentArgs: The arguments to resource properties.
opts CustomResourceOptions: Bag of options to control resource's behavior.

Agent Resource Properties

To learn more about resource properties and how to use them, see Inputs and Outputs in the Programming Model docs.

Inputs

The Agent resource accepts the following input properties:

DefaultLanguageCode string: 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 updated after creation.
DisplayName string: The name of this agent.
TimeZone string: The time zone of this agent from the time zone database, e.g., America/New_York, Europe/Paris.
ApiVersion string: 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. * API_VERSION_V1: Legacy V1 API. * API_VERSION_V2: V2 API. * API_VERSION_V2_BETA_1: V2beta1 API.
AvatarUri string: The URI of the agent’s avatar, which are used throughout the Dialogflow console. When an image URL is entered into this field, the Dialogflow will save the image in the backend. The address of the backend image returned from the API will be shown in the [avatarUriBackend] field.
ClassificationThreshold double: 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.
Description string: The description of this agent. The maximum length is 500 characters. If exceeded, the request is rejected.
EnableLogging bool: Determines whether this agent should log conversation queries.
MatchMode string: Determines how intents are detected from user queries. * 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 developer entities.
Project string: The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
SupportedLanguageCodes List<string>: The list of all languages supported by this agent (except for the defaultLanguageCode).
Tier string: The agent tier. If not specified, TIER_STANDARD is assumed. * TIER_STANDARD: Standard tier. * TIER_ENTERPRISE: Enterprise tier (Essentials). * TIER_ENTERPRISE_PLUS: Enterprise tier (Plus). NOTE: Due to consistency issues, the provider will not read this field from the API. Drift is possible between the the provider state and Dialogflow if the agent tier is changed outside of the provider.

DefaultLanguageCode string: 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 updated after creation.
DisplayName string: The name of this agent.
TimeZone string: The time zone of this agent from the time zone database, e.g., America/New_York, Europe/Paris.
ApiVersion string: 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. * API_VERSION_V1: Legacy V1 API. * API_VERSION_V2: V2 API. * API_VERSION_V2_BETA_1: V2beta1 API.
AvatarUri string: The URI of the agent’s avatar, which are used throughout the Dialogflow console. When an image URL is entered into this field, the Dialogflow will save the image in the backend. The address of the backend image returned from the API will be shown in the [avatarUriBackend] field.
ClassificationThreshold float64: 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.
Description string: The description of this agent. The maximum length is 500 characters. If exceeded, the request is rejected.
EnableLogging bool: Determines whether this agent should log conversation queries.
MatchMode string: Determines how intents are detected from user queries. * 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 developer entities.
Project string: The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
SupportedLanguageCodes []string: The list of all languages supported by this agent (except for the defaultLanguageCode).
Tier string: The agent tier. If not specified, TIER_STANDARD is assumed. * TIER_STANDARD: Standard tier. * TIER_ENTERPRISE: Enterprise tier (Essentials). * TIER_ENTERPRISE_PLUS: Enterprise tier (Plus). NOTE: Due to consistency issues, the provider will not read this field from the API. Drift is possible between the the provider state and Dialogflow if the agent tier is changed outside of the provider.

defaultLanguageCode string: 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 updated after creation.
displayName string: The name of this agent.
timeZone string: The time zone of this agent from the time zone database, e.g., America/New_York, Europe/Paris.
apiVersion string: 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. * API_VERSION_V1: Legacy V1 API. * API_VERSION_V2: V2 API. * API_VERSION_V2_BETA_1: V2beta1 API.
avatarUri string: The URI of the agent’s avatar, which are used throughout the Dialogflow console. When an image URL is entered into this field, the Dialogflow will save the image in the backend. The address of the backend image returned from the API will be shown in the [avatarUriBackend] field.
classificationThreshold number: 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.
description string: The description of this agent. The maximum length is 500 characters. If exceeded, the request is rejected.
enableLogging boolean: Determines whether this agent should log conversation queries.
matchMode string: Determines how intents are detected from user queries. * 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 developer entities.
project string: The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
supportedLanguageCodes string[]: The list of all languages supported by this agent (except for the defaultLanguageCode).
tier string: The agent tier. If not specified, TIER_STANDARD is assumed. * TIER_STANDARD: Standard tier. * TIER_ENTERPRISE: Enterprise tier (Essentials). * TIER_ENTERPRISE_PLUS: Enterprise tier (Plus). NOTE: Due to consistency issues, the provider will not read this field from the API. Drift is possible between the the provider state and Dialogflow if the agent tier is changed outside of the provider.

default_language_code str: 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 updated after creation.
display_name str: The name of this agent.
time_zone str: The time zone of this agent from the time zone database, e.g., America/New_York, Europe/Paris.
api_version str: 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. * API_VERSION_V1: Legacy V1 API. * API_VERSION_V2: V2 API. * API_VERSION_V2_BETA_1: V2beta1 API.
avatar_uri str: The URI of the agent’s avatar, which are used throughout the Dialogflow console. When an image URL is entered into this field, the Dialogflow will save the image in the backend. The address of the backend image returned from the API will be shown in the [avatarUriBackend] field.
classification_threshold float: 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.
description str: The description of this agent. The maximum length is 500 characters. If exceeded, the request is rejected.
enable_logging bool: Determines whether this agent should log conversation queries.
match_mode str: Determines how intents are detected from user queries. * 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 developer entities.
project str: The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
supported_language_codes List[str]: The list of all languages supported by this agent (except for the defaultLanguageCode).
tier str: The agent tier. If not specified, TIER_STANDARD is assumed. * TIER_STANDARD: Standard tier. * TIER_ENTERPRISE: Enterprise tier (Essentials). * TIER_ENTERPRISE_PLUS: Enterprise tier (Plus). NOTE: Due to consistency issues, the provider will not read this field from the API. Drift is possible between the the provider state and Dialogflow if the agent tier is changed outside of the provider.

Outputs

All input properties are implicitly available as output properties. Additionally, the Agent resource produces the following output properties:

AvatarUriBackend string: The URI of the agent’s avatar as returned from the API. Output only. To provide an image URL for the agent avatar, the [avatarUri] field can be used.
Id string: The provider-assigned unique ID for this managed resource.

AvatarUriBackend string: The URI of the agent’s avatar as returned from the API. Output only. To provide an image URL for the agent avatar, the [avatarUri] field can be used.
Id string: The provider-assigned unique ID for this managed resource.

avatarUriBackend string: The URI of the agent’s avatar as returned from the API. Output only. To provide an image URL for the agent avatar, the [avatarUri] field can be used.
id string: The provider-assigned unique ID for this managed resource.

avatar_uri_backend str: The URI of the agent’s avatar as returned from the API. Output only. To provide an image URL for the agent avatar, the [avatarUri] field can be used.
id str: The provider-assigned unique ID for this managed resource.

Look up an Existing Agent Resource

Get an existing Agent resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.

public static get(name: string, id: Input<ID>, state?: AgentState, opts?: CustomResourceOptions): Agent

static get(resource_name, id, opts=None, api_version=None, avatar_uri=None, avatar_uri_backend=None, classification_threshold=None, default_language_code=None, description=None, display_name=None, enable_logging=None, match_mode=None, project=None, supported_language_codes=None, tier=None, time_zone=None, __props__=None);

func GetAgent(ctx *Context, name string, id IDInput, state *AgentState, opts ...ResourceOption) (*Agent, error)

public static Agent Get(string name, Input<string> id, AgentState? state, CustomResourceOptions? opts = null)

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

resource_name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

The following state arguments are supported:

ApiVersion string: 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. * API_VERSION_V1: Legacy V1 API. * API_VERSION_V2: V2 API. * API_VERSION_V2_BETA_1: V2beta1 API.
AvatarUri string: The URI of the agent’s avatar, which are used throughout the Dialogflow console. When an image URL is entered into this field, the Dialogflow will save the image in the backend. The address of the backend image returned from the API will be shown in the [avatarUriBackend] field.
AvatarUriBackend string: The URI of the agent’s avatar as returned from the API. Output only. To provide an image URL for the agent avatar, the [avatarUri] field can be used.
ClassificationThreshold double: 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.
DefaultLanguageCode string: 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 updated after creation.
Description string: The description of this agent. The maximum length is 500 characters. If exceeded, the request is rejected.
DisplayName string: The name of this agent.
EnableLogging bool: Determines whether this agent should log conversation queries.
MatchMode string: Determines how intents are detected from user queries. * 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 developer entities.
Project string: The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
SupportedLanguageCodes List<string>: The list of all languages supported by this agent (except for the defaultLanguageCode).
Tier string: The agent tier. If not specified, TIER_STANDARD is assumed. * TIER_STANDARD: Standard tier. * TIER_ENTERPRISE: Enterprise tier (Essentials). * TIER_ENTERPRISE_PLUS: Enterprise tier (Plus). NOTE: Due to consistency issues, the provider will not read this field from the API. Drift is possible between the the provider state and Dialogflow if the agent tier is changed outside of the provider.
TimeZone string: The time zone of this agent from the time zone database, e.g., America/New_York, Europe/Paris.

ApiVersion string: 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. * API_VERSION_V1: Legacy V1 API. * API_VERSION_V2: V2 API. * API_VERSION_V2_BETA_1: V2beta1 API.
AvatarUri string: The URI of the agent’s avatar, which are used throughout the Dialogflow console. When an image URL is entered into this field, the Dialogflow will save the image in the backend. The address of the backend image returned from the API will be shown in the [avatarUriBackend] field.
AvatarUriBackend string: The URI of the agent’s avatar as returned from the API. Output only. To provide an image URL for the agent avatar, the [avatarUri] field can be used.
ClassificationThreshold float64: 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.
DefaultLanguageCode string: 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 updated after creation.
Description string: The description of this agent. The maximum length is 500 characters. If exceeded, the request is rejected.
DisplayName string: The name of this agent.
EnableLogging bool: Determines whether this agent should log conversation queries.
MatchMode string: Determines how intents are detected from user queries. * 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 developer entities.
Project string: The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
SupportedLanguageCodes []string: The list of all languages supported by this agent (except for the defaultLanguageCode).
Tier string: The agent tier. If not specified, TIER_STANDARD is assumed. * TIER_STANDARD: Standard tier. * TIER_ENTERPRISE: Enterprise tier (Essentials). * TIER_ENTERPRISE_PLUS: Enterprise tier (Plus). NOTE: Due to consistency issues, the provider will not read this field from the API. Drift is possible between the the provider state and Dialogflow if the agent tier is changed outside of the provider.
TimeZone string: The time zone of this agent from the time zone database, e.g., America/New_York, Europe/Paris.

apiVersion string: 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. * API_VERSION_V1: Legacy V1 API. * API_VERSION_V2: V2 API. * API_VERSION_V2_BETA_1: V2beta1 API.
avatarUri string: The URI of the agent’s avatar, which are used throughout the Dialogflow console. When an image URL is entered into this field, the Dialogflow will save the image in the backend. The address of the backend image returned from the API will be shown in the [avatarUriBackend] field.
avatarUriBackend string: The URI of the agent’s avatar as returned from the API. Output only. To provide an image URL for the agent avatar, the [avatarUri] field can be used.
classificationThreshold number: 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.
defaultLanguageCode string: 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 updated after creation.
description string: The description of this agent. The maximum length is 500 characters. If exceeded, the request is rejected.
displayName string: The name of this agent.
enableLogging boolean: Determines whether this agent should log conversation queries.
matchMode string: Determines how intents are detected from user queries. * 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 developer entities.
project string: The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
supportedLanguageCodes string[]: The list of all languages supported by this agent (except for the defaultLanguageCode).
tier string: The agent tier. If not specified, TIER_STANDARD is assumed. * TIER_STANDARD: Standard tier. * TIER_ENTERPRISE: Enterprise tier (Essentials). * TIER_ENTERPRISE_PLUS: Enterprise tier (Plus). NOTE: Due to consistency issues, the provider will not read this field from the API. Drift is possible between the the provider state and Dialogflow if the agent tier is changed outside of the provider.
timeZone string: The time zone of this agent from the time zone database, e.g., America/New_York, Europe/Paris.

api_version str: 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. * API_VERSION_V1: Legacy V1 API. * API_VERSION_V2: V2 API. * API_VERSION_V2_BETA_1: V2beta1 API.
avatar_uri str: The URI of the agent’s avatar, which are used throughout the Dialogflow console. When an image URL is entered into this field, the Dialogflow will save the image in the backend. The address of the backend image returned from the API will be shown in the [avatarUriBackend] field.
avatar_uri_backend str: The URI of the agent’s avatar as returned from the API. Output only. To provide an image URL for the agent avatar, the [avatarUri] field can be used.
classification_threshold float: 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.
default_language_code str: 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 updated after creation.
description str: The description of this agent. The maximum length is 500 characters. If exceeded, the request is rejected.
display_name str: The name of this agent.
enable_logging bool: Determines whether this agent should log conversation queries.
match_mode str: Determines how intents are detected from user queries. * 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 developer entities.
project str: The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
supported_language_codes List[str]: The list of all languages supported by this agent (except for the defaultLanguageCode).
tier str: The agent tier. If not specified, TIER_STANDARD is assumed. * TIER_STANDARD: Standard tier. * TIER_ENTERPRISE: Enterprise tier (Essentials). * TIER_ENTERPRISE_PLUS: Enterprise tier (Plus). NOTE: Due to consistency issues, the provider will not read this field from the API. Drift is possible between the the provider state and Dialogflow if the agent tier is changed outside of the provider.
time_zone str: The time zone of this agent from the time zone database, e.g., America/New_York, Europe/Paris.

Package Details

Repository: https://github.com/pulumi/pulumi-gcp
License: Apache-2.0
Notes: This Pulumi package is based on the google-beta Terraform Provider.

The Pulumi Platform

Get Started

Migrate to Pulumi

Solutions for All Teams and Engineers

Any Code

Any Cloud