2026/06/12 - Amazon Bedrock AgentCore Control - 8 updated api methods
Changes Added tagging and CMK support across optimization, an explanation field in recommendation output, and an insights feature to identify failure patterns, extract user intents, and summarize execution behavior
{'kmsKeyArn': 'string'}
Creates a new configuration bundle resource. A configuration bundle stores versioned component configurations for agent evaluation workflows.
See also: AWS API Documentation
Request Syntax
client.create_configuration_bundle(
clientToken='string',
bundleName='string',
description='string',
components={
'string': {
'configuration': {...}|[...]|123|123.4|'string'|True|None
}
},
branchName='string',
commitMessage='string',
createdBy={
'name': 'string',
'arn': 'string'
},
kmsKeyArn='string',
tags={
'string': 'string'
}
)
string
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If you don't specify this field, a value is randomly generated for you. If this token matches a previous request, the service ignores the request, but doesn't return an error. For more information, see Ensuring idempotency.
This field is autopopulated if not provided.
string
[REQUIRED]
The name for the configuration bundle. Names must be unique within your account.
string
The description for the configuration bundle.
dict
[REQUIRED]
A map of component identifiers to their configurations. Each component represents a configurable element within the bundle.
(string) --
(dict) --
The configuration for a component within a configuration bundle. The component type is inferred from the component identifier ARN.
configuration (:ref:`document<document>`) -- [REQUIRED]
The configuration values as a flexible JSON document.
string
The branch name for version tracking. Defaults to mainline if not specified.
string
A commit message describing the initial version of the configuration bundle.
dict
The source that created this version, including the source name and optional ARN.
name (string) -- [REQUIRED]
The name of the source (for example, user, optimization-job, or system).
arn (string) --
The Amazon Resource Name (ARN) of the source, if applicable (for example, a user ARN or optimization job ARN).
string
Optional KMS key ARN for encrypting component configurations.
dict
A map of tag keys and values to assign to the configuration bundle. Tags enable you to categorize your resources in different ways, for example, by purpose, owner, or environment.
(string) --
(string) --
dict
Response Syntax
{
'bundleArn': 'string',
'bundleId': 'string',
'versionId': 'string',
'createdAt': datetime(2015, 1, 1)
}
Response Structure
(dict) --
bundleArn (string) --
The Amazon Resource Name (ARN) of the created configuration bundle.
bundleId (string) --
The unique identifier of the created configuration bundle.
versionId (string) --
The initial version identifier of the configuration bundle.
createdAt (datetime) --
The timestamp when the configuration bundle was created.
{'clusteringConfig': {'frequencies': ['DAILY | WEEKLY | MONTHLY']},
'insights': [{'insightId': 'string'}]}
Creates an online evaluation configuration for continuous monitoring of agent performance. Online evaluation automatically samples live traffic from CloudWatch logs at specified rates and applies evaluators to assess agent quality in production.
See also: AWS API Documentation
Request Syntax
client.create_online_evaluation_config(
clientToken='string',
onlineEvaluationConfigName='string',
description='string',
rule={
'samplingConfig': {
'samplingPercentage': 123.0
},
'filters': [
{
'key': 'string',
'operator': 'Equals'|'NotEquals'|'GreaterThan'|'LessThan'|'GreaterThanOrEqual'|'LessThanOrEqual'|'Contains'|'NotContains',
'value': {
'stringValue': 'string',
'doubleValue': 123.0,
'booleanValue': True|False
}
},
],
'sessionConfig': {
'sessionTimeoutMinutes': 123
}
},
dataSourceConfig={
'cloudWatchLogs': {
'logGroupNames': [
'string',
],
'serviceNames': [
'string',
]
}
},
evaluators=[
{
'evaluatorId': 'string'
},
],
insights=[
{
'insightId': 'string'
},
],
clusteringConfig={
'frequencies': [
'DAILY'|'WEEKLY'|'MONTHLY',
]
},
evaluationExecutionRoleArn='string',
enableOnCreate=True|False,
tags={
'string': 'string'
}
)
string
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If you don't specify this field, a value is randomly generated for you. If this token matches a previous request, the service ignores the request, but doesn't return an error. For more information, see Ensuring idempotency.
This field is autopopulated if not provided.
string
[REQUIRED]
The name of the online evaluation configuration. Must be unique within your account.
string
The description of the online evaluation configuration that explains its monitoring purpose and scope.
dict
[REQUIRED]
The evaluation rule that defines sampling configuration, filters, and session detection settings for the online evaluation.
samplingConfig (dict) -- [REQUIRED]
The sampling configuration that determines what percentage of agent traces to evaluate.
samplingPercentage (float) -- [REQUIRED]
The percentage of agent traces to sample for evaluation, ranging from 0.01% to 100%.
filters (list) --
The list of filters that determine which agent traces should be included in the evaluation based on trace properties.
(dict) --
The filter that applies conditions to agent traces during online evaluation to determine which traces should be evaluated.
key (string) -- [REQUIRED]
The key or field name to filter on within the agent trace data.
operator (string) -- [REQUIRED]
The comparison operator to use for filtering.
value (dict) -- [REQUIRED]
The value to compare against using the specified operator.
stringValue (string) --
The string value for text-based filtering.
doubleValue (float) --
The numeric value for numerical filtering and comparisons.
booleanValue (boolean) --
The boolean value for true/false filtering conditions.
sessionConfig (dict) --
The session configuration that defines timeout settings for detecting when agent sessions are complete and ready for evaluation.
sessionTimeoutMinutes (integer) -- [REQUIRED]
The number of minutes of inactivity after which an agent session is considered complete and ready for evaluation. Default is 15 minutes.
dict
[REQUIRED]
The data source configuration that specifies CloudWatch log groups and service names to monitor for agent traces.
cloudWatchLogs (dict) --
The CloudWatch logs configuration for reading agent traces from log groups.
logGroupNames (list) -- [REQUIRED]
The list of CloudWatch log group names to monitor for agent traces.
(string) --
serviceNames (list) -- [REQUIRED]
The list of service names to filter traces within the specified log groups. Used to identify relevant agent sessions.
(string) --
list
The list of evaluators to apply during online evaluation. Can include both built-in evaluators and custom evaluators created with CreateEvaluator.
(dict) --
The reference to an evaluator used in online evaluation configurations, containing the evaluator identifier.
evaluatorId (string) --
The unique identifier of the evaluator. Can reference builtin evaluators (e.g., Builtin.Helpfulness) or custom evaluators.
list
The list of insight types to run against agent sessions.
(dict) --
A reference to an insight analysis to run against sessions.
insightId (string) -- [REQUIRED]
Canonical insight identifiers using the Builtin.Insight.* naming convention. Used by BatchEvaluate, InternalEvaluate, and ServiceEngineEvaluate flows.
dict
Configuration for periodic batch evaluation clustering of insight results.
frequencies (list) -- [REQUIRED]
The list of frequencies at which clustering batch evaluations are triggered.
(string) --
string
[REQUIRED]
The Amazon Resource Name (ARN) of the IAM role that grants permissions to read from CloudWatch logs, write evaluation results, and invoke Amazon Bedrock models for evaluation. If the configuration references evaluators encrypted with a customer managed KMS key, this role must also have kms:Decrypt permission on the KMS key. The service validates this permission at configuration creation time. For more information, see Encryption at rest for AgentCore Evaluations.
boolean
[REQUIRED]
Whether to enable the online evaluation configuration immediately upon creation. If true, evaluation begins automatically.
dict
A map of tag keys and values to assign to an AgentCore Online Evaluation Config. Tags enable you to categorize your resources in different ways, for example, by purpose, owner, or environment.
(string) --
(string) --
dict
Response Syntax
{
'onlineEvaluationConfigArn': 'string',
'onlineEvaluationConfigId': 'string',
'createdAt': datetime(2015, 1, 1),
'outputConfig': {
'cloudWatchConfig': {
'logGroupName': 'string'
}
},
'status': 'ACTIVE'|'CREATING'|'CREATE_FAILED'|'UPDATING'|'UPDATE_FAILED'|'DELETING'|'ERROR',
'executionStatus': 'ENABLED'|'DISABLED',
'failureReason': 'string'
}
Response Structure
(dict) --
onlineEvaluationConfigArn (string) --
The Amazon Resource Name (ARN) of the created online evaluation configuration.
onlineEvaluationConfigId (string) --
The unique identifier of the created online evaluation configuration.
createdAt (datetime) --
The timestamp when the online evaluation configuration was created.
outputConfig (dict) --
The configuration that specifies where evaluation results should be written for monitoring and analysis.
cloudWatchConfig (dict) --
The CloudWatch configuration for writing evaluation results to CloudWatch logs with embedded metric format.
logGroupName (string) --
The name of the CloudWatch log group where evaluation results will be written. The log group will be created if it doesn't exist.
status (string) --
The status of the online evaluation configuration.
executionStatus (string) --
The execution status indicating whether the online evaluation is currently running.
failureReason (string) --
The reason for failure if the online evaluation configuration creation or execution failed.
{'kmsKeyArn': 'string'}
Gets the latest version of a configuration bundle. By default, returns the latest version on the mainline branch. Use GetConfigurationBundleVersion to retrieve a specific historical version.
See also: AWS API Documentation
Request Syntax
client.get_configuration_bundle(
bundleId='string',
branchName='string'
)
string
[REQUIRED]
The unique identifier of the configuration bundle to retrieve.
string
The branch name to get the latest version from. If not specified, returns the latest version on the mainline branch.
dict
Response Syntax
{
'bundleArn': 'string',
'bundleId': 'string',
'bundleName': 'string',
'description': 'string',
'versionId': 'string',
'components': {
'string': {
'configuration': {...}|[...]|123|123.4|'string'|True|None
}
},
'lineageMetadata': {
'parentVersionIds': [
'string',
],
'branchName': 'string',
'createdBy': {
'name': 'string',
'arn': 'string'
},
'commitMessage': 'string'
},
'createdAt': datetime(2015, 1, 1),
'updatedAt': datetime(2015, 1, 1),
'kmsKeyArn': 'string'
}
Response Structure
(dict) --
bundleArn (string) --
The Amazon Resource Name (ARN) of the configuration bundle.
bundleId (string) --
The unique identifier of the configuration bundle.
bundleName (string) --
The name of the configuration bundle.
description (string) --
The description of the configuration bundle.
versionId (string) --
The version identifier of this configuration bundle.
components (dict) --
A map of component identifiers to their configurations for this version.
(string) --
(dict) --
The configuration for a component within a configuration bundle. The component type is inferred from the component identifier ARN.
configuration (:ref:`document<document>`) --
The configuration values as a flexible JSON document.
lineageMetadata (dict) --
The version lineage metadata, including parent versions, branch name, and creation source.
parentVersionIds (list) --
A list of parent version identifiers. Regular commits have 0-1 parents. Merge commits have 2 parents: the target branch parent and the source branch parent. The first parent represents the primary lineage.
(string) --
branchName (string) --
The branch name for this version. If not specified, inherits the parent's branch or defaults to mainline.
createdBy (dict) --
The source that created this version.
name (string) --
The name of the source (for example, user, optimization-job, or system).
arn (string) --
The Amazon Resource Name (ARN) of the source, if applicable (for example, a user ARN or optimization job ARN).
commitMessage (string) --
A commit message describing the changes in this version.
createdAt (datetime) --
The timestamp when the configuration bundle was created.
updatedAt (datetime) --
The timestamp when the configuration bundle was last updated.
kmsKeyArn (string) --
KMS key ARN used to encrypt component configurations, if CMK was provided.
{'kmsKeyArn': 'string'}
Gets a specific version of a configuration bundle by its version identifier.
See also: AWS API Documentation
Request Syntax
client.get_configuration_bundle_version(
bundleId='string',
versionId='string'
)
string
[REQUIRED]
The unique identifier of the configuration bundle.
string
[REQUIRED]
The version identifier of the configuration bundle version to retrieve.
dict
Response Syntax
{
'bundleArn': 'string',
'bundleId': 'string',
'bundleName': 'string',
'description': 'string',
'versionId': 'string',
'components': {
'string': {
'configuration': {...}|[...]|123|123.4|'string'|True|None
}
},
'lineageMetadata': {
'parentVersionIds': [
'string',
],
'branchName': 'string',
'createdBy': {
'name': 'string',
'arn': 'string'
},
'commitMessage': 'string'
},
'createdAt': datetime(2015, 1, 1),
'versionCreatedAt': datetime(2015, 1, 1),
'kmsKeyArn': 'string'
}
Response Structure
(dict) --
bundleArn (string) --
The Amazon Resource Name (ARN) of the configuration bundle.
bundleId (string) --
The unique identifier of the configuration bundle.
bundleName (string) --
The name of the configuration bundle.
description (string) --
The description of the configuration bundle.
versionId (string) --
The version identifier of this configuration bundle version.
components (dict) --
A map of component identifiers to their configurations for this version.
(string) --
(dict) --
The configuration for a component within a configuration bundle. The component type is inferred from the component identifier ARN.
configuration (:ref:`document<document>`) --
The configuration values as a flexible JSON document.
lineageMetadata (dict) --
The version lineage metadata, including parent versions, branch name, and creation source.
parentVersionIds (list) --
A list of parent version identifiers. Regular commits have 0-1 parents. Merge commits have 2 parents: the target branch parent and the source branch parent. The first parent represents the primary lineage.
(string) --
branchName (string) --
The branch name for this version. If not specified, inherits the parent's branch or defaults to mainline.
createdBy (dict) --
The source that created this version.
name (string) --
The name of the source (for example, user, optimization-job, or system).
arn (string) --
The Amazon Resource Name (ARN) of the source, if applicable (for example, a user ARN or optimization job ARN).
commitMessage (string) --
A commit message describing the changes in this version.
createdAt (datetime) --
The timestamp when the configuration bundle was created.
versionCreatedAt (datetime) --
The timestamp when this specific version was created.
kmsKeyArn (string) --
KMS key ARN used to encrypt component configurations, if CMK was provided.
{'clusteringConfig': {'frequencies': ['DAILY | WEEKLY | MONTHLY']},
'insights': [{'insightId': 'string'}]}
Retrieves detailed information about an online evaluation configuration, including its rules, data sources, evaluators, and execution status.
See also: AWS API Documentation
Request Syntax
client.get_online_evaluation_config(
onlineEvaluationConfigId='string'
)
string
[REQUIRED]
The unique identifier of the online evaluation configuration to retrieve.
dict
Response Syntax
{
'onlineEvaluationConfigArn': 'string',
'onlineEvaluationConfigId': 'string',
'onlineEvaluationConfigName': 'string',
'description': 'string',
'rule': {
'samplingConfig': {
'samplingPercentage': 123.0
},
'filters': [
{
'key': 'string',
'operator': 'Equals'|'NotEquals'|'GreaterThan'|'LessThan'|'GreaterThanOrEqual'|'LessThanOrEqual'|'Contains'|'NotContains',
'value': {
'stringValue': 'string',
'doubleValue': 123.0,
'booleanValue': True|False
}
},
],
'sessionConfig': {
'sessionTimeoutMinutes': 123
}
},
'dataSourceConfig': {
'cloudWatchLogs': {
'logGroupNames': [
'string',
],
'serviceNames': [
'string',
]
}
},
'evaluators': [
{
'evaluatorId': 'string'
},
],
'insights': [
{
'insightId': 'string'
},
],
'clusteringConfig': {
'frequencies': [
'DAILY'|'WEEKLY'|'MONTHLY',
]
},
'outputConfig': {
'cloudWatchConfig': {
'logGroupName': 'string'
}
},
'evaluationExecutionRoleArn': 'string',
'status': 'ACTIVE'|'CREATING'|'CREATE_FAILED'|'UPDATING'|'UPDATE_FAILED'|'DELETING'|'ERROR',
'executionStatus': 'ENABLED'|'DISABLED',
'createdAt': datetime(2015, 1, 1),
'updatedAt': datetime(2015, 1, 1),
'failureReason': 'string'
}
Response Structure
(dict) --
onlineEvaluationConfigArn (string) --
The Amazon Resource Name (ARN) of the online evaluation configuration.
onlineEvaluationConfigId (string) --
The unique identifier of the online evaluation configuration.
onlineEvaluationConfigName (string) --
The name of the online evaluation configuration.
description (string) --
The description of the online evaluation configuration.
rule (dict) --
The evaluation rule containing sampling configuration, filters, and session settings.
samplingConfig (dict) --
The sampling configuration that determines what percentage of agent traces to evaluate.
samplingPercentage (float) --
The percentage of agent traces to sample for evaluation, ranging from 0.01% to 100%.
filters (list) --
The list of filters that determine which agent traces should be included in the evaluation based on trace properties.
(dict) --
The filter that applies conditions to agent traces during online evaluation to determine which traces should be evaluated.
key (string) --
The key or field name to filter on within the agent trace data.
operator (string) --
The comparison operator to use for filtering.
value (dict) --
The value to compare against using the specified operator.
stringValue (string) --
The string value for text-based filtering.
doubleValue (float) --
The numeric value for numerical filtering and comparisons.
booleanValue (boolean) --
The boolean value for true/false filtering conditions.
sessionConfig (dict) --
The session configuration that defines timeout settings for detecting when agent sessions are complete and ready for evaluation.
sessionTimeoutMinutes (integer) --
The number of minutes of inactivity after which an agent session is considered complete and ready for evaluation. Default is 15 minutes.
dataSourceConfig (dict) --
The data source configuration specifying CloudWatch log groups and service names to monitor.
cloudWatchLogs (dict) --
The CloudWatch logs configuration for reading agent traces from log groups.
logGroupNames (list) --
The list of CloudWatch log group names to monitor for agent traces.
(string) --
serviceNames (list) --
The list of service names to filter traces within the specified log groups. Used to identify relevant agent sessions.
(string) --
evaluators (list) --
The list of evaluators applied during online evaluation.
(dict) --
The reference to an evaluator used in online evaluation configurations, containing the evaluator identifier.
evaluatorId (string) --
The unique identifier of the evaluator. Can reference builtin evaluators (e.g., Builtin.Helpfulness) or custom evaluators.
insights (list) --
The list of insight types configured for this evaluation.
(dict) --
A reference to an insight analysis to run against sessions.
insightId (string) --
Canonical insight identifiers using the Builtin.Insight.* naming convention. Used by BatchEvaluate, InternalEvaluate, and ServiceEngineEvaluate flows.
clusteringConfig (dict) --
The clustering configuration for periodic batch evaluation.
frequencies (list) --
The list of frequencies at which clustering batch evaluations are triggered.
(string) --
outputConfig (dict) --
The output configuration specifying where evaluation results are written.
cloudWatchConfig (dict) --
The CloudWatch configuration for writing evaluation results to CloudWatch logs with embedded metric format.
logGroupName (string) --
The name of the CloudWatch log group where evaluation results will be written. The log group will be created if it doesn't exist.
evaluationExecutionRoleArn (string) --
The Amazon Resource Name (ARN) of the IAM role used for evaluation execution.
status (string) --
The status of the online evaluation configuration.
executionStatus (string) --
The execution status indicating whether the online evaluation is currently running.
createdAt (datetime) --
The timestamp when the online evaluation configuration was created.
updatedAt (datetime) --
The timestamp when the online evaluation configuration was last updated.
failureReason (string) --
The reason for failure if the online evaluation configuration execution failed.
{'onlineEvaluationConfigs': {'clusteringConfig': {'frequencies': ['DAILY | '
'WEEKLY | '
'MONTHLY']},
'insights': [{'insightId': 'string'}]}}
Lists all online evaluation configurations in the account, providing summary information about each configuration's status and settings.
See also: AWS API Documentation
Request Syntax
client.list_online_evaluation_configs(
nextToken='string',
maxResults=123
)
string
The pagination token from a previous request to retrieve the next page of results.
integer
The maximum number of online evaluation configurations to return in a single response.
dict
Response Syntax
{
'onlineEvaluationConfigs': [
{
'onlineEvaluationConfigArn': 'string',
'onlineEvaluationConfigId': 'string',
'onlineEvaluationConfigName': 'string',
'description': 'string',
'status': 'ACTIVE'|'CREATING'|'CREATE_FAILED'|'UPDATING'|'UPDATE_FAILED'|'DELETING'|'ERROR',
'executionStatus': 'ENABLED'|'DISABLED',
'createdAt': datetime(2015, 1, 1),
'updatedAt': datetime(2015, 1, 1),
'failureReason': 'string',
'insights': [
{
'insightId': 'string'
},
],
'clusteringConfig': {
'frequencies': [
'DAILY'|'WEEKLY'|'MONTHLY',
]
}
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
onlineEvaluationConfigs (list) --
The list of online evaluation configuration summaries containing basic information about each configuration.
(dict) --
The summary information about an online evaluation configuration, including basic metadata and execution status.
onlineEvaluationConfigArn (string) --
The Amazon Resource Name (ARN) of the online evaluation configuration.
onlineEvaluationConfigId (string) --
The unique identifier of the online evaluation configuration.
onlineEvaluationConfigName (string) --
The name of the online evaluation configuration.
description (string) --
The description of the online evaluation configuration.
status (string) --
The status of the online evaluation configuration.
executionStatus (string) --
The execution status indicating whether the online evaluation is currently running.
createdAt (datetime) --
The timestamp when the online evaluation configuration was created.
updatedAt (datetime) --
The timestamp when the online evaluation configuration was last updated.
failureReason (string) --
The reason for failure if the online evaluation configuration execution failed.
insights (list) --
The list of insight types configured for this evaluation.
(dict) --
A reference to an insight analysis to run against sessions.
insightId (string) --
Canonical insight identifiers using the Builtin.Insight.* naming convention. Used by BatchEvaluate, InternalEvaluate, and ServiceEngineEvaluate flows.
clusteringConfig (dict) --
The clustering configuration for periodic batch evaluation.
frequencies (list) --
The list of frequencies at which clustering batch evaluations are triggered.
(string) --
nextToken (string) --
The pagination token to use in a subsequent request to retrieve the next page of results.
{'kmsKeyArn': 'string'}
Updates a configuration bundle by creating a new version with the specified changes. Each update creates a new version in the version history.
See also: AWS API Documentation
Request Syntax
client.update_configuration_bundle(
clientToken='string',
bundleId='string',
bundleName='string',
description='string',
components={
'string': {
'configuration': {...}|[...]|123|123.4|'string'|True|None
}
},
parentVersionIds=[
'string',
],
branchName='string',
commitMessage='string',
createdBy={
'name': 'string',
'arn': 'string'
},
kmsKeyArn='string'
)
string
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If you don't specify this field, a value is randomly generated for you. If this token matches a previous request, the service ignores the request, but doesn't return an error. For more information, see Ensuring idempotency.
This field is autopopulated if not provided.
string
[REQUIRED]
The unique identifier of the configuration bundle to update.
string
The updated name for the configuration bundle.
string
The updated description for the configuration bundle.
dict
The updated component configurations. Creates a new version of the bundle.
(string) --
(dict) --
The configuration for a component within a configuration bundle. The component type is inferred from the component identifier ARN.
configuration (:ref:`document<document>`) -- [REQUIRED]
The configuration values as a flexible JSON document.
list
A list of parent version identifiers for lineage tracking. Regular commits have a single parent. Merge commits have two parents: the target branch parent and the source branch parent. If the branch already exists, the first parent must be the latest version on that branch.
(string) --
string
The branch name for this version. If not specified, inherits the parent's branch or defaults to mainline.
string
A commit message describing the changes in this version.
dict
The source that created this version, including the source name and optional ARN.
name (string) -- [REQUIRED]
The name of the source (for example, user, optimization-job, or system).
arn (string) --
The Amazon Resource Name (ARN) of the source, if applicable (for example, a user ARN or optimization job ARN).
string
Optional KMS key ARN for encrypting component configurations. If provided, components will be encrypted with this key. If the bundle already has a KMS key, this rotates to the new key.
dict
Response Syntax
{
'bundleArn': 'string',
'bundleId': 'string',
'versionId': 'string',
'updatedAt': datetime(2015, 1, 1)
}
Response Structure
(dict) --
bundleArn (string) --
The Amazon Resource Name (ARN) of the updated configuration bundle.
bundleId (string) --
The unique identifier of the updated configuration bundle.
versionId (string) --
The new version identifier created by this update.
updatedAt (datetime) --
The timestamp when the configuration bundle was updated.
{'clusteringConfig': {'frequencies': ['DAILY | WEEKLY | MONTHLY']},
'insights': [{'insightId': 'string'}]}
Updates an online evaluation configuration's settings, including rules, data sources, evaluators, and execution status. Changes take effect immediately for ongoing evaluations.
See also: AWS API Documentation
Request Syntax
client.update_online_evaluation_config(
clientToken='string',
onlineEvaluationConfigId='string',
description='string',
rule={
'samplingConfig': {
'samplingPercentage': 123.0
},
'filters': [
{
'key': 'string',
'operator': 'Equals'|'NotEquals'|'GreaterThan'|'LessThan'|'GreaterThanOrEqual'|'LessThanOrEqual'|'Contains'|'NotContains',
'value': {
'stringValue': 'string',
'doubleValue': 123.0,
'booleanValue': True|False
}
},
],
'sessionConfig': {
'sessionTimeoutMinutes': 123
}
},
dataSourceConfig={
'cloudWatchLogs': {
'logGroupNames': [
'string',
],
'serviceNames': [
'string',
]
}
},
evaluators=[
{
'evaluatorId': 'string'
},
],
insights=[
{
'insightId': 'string'
},
],
clusteringConfig={
'frequencies': [
'DAILY'|'WEEKLY'|'MONTHLY',
]
},
evaluationExecutionRoleArn='string',
executionStatus='ENABLED'|'DISABLED'
)
string
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If you don't specify this field, a value is randomly generated for you. If this token matches a previous request, the service ignores the request, but doesn't return an error. For more information, see Ensuring idempotency.
This field is autopopulated if not provided.
string
[REQUIRED]
The unique identifier of the online evaluation configuration to update.
string
The updated description of the online evaluation configuration.
dict
The updated evaluation rule containing sampling configuration, filters, and session settings.
samplingConfig (dict) -- [REQUIRED]
The sampling configuration that determines what percentage of agent traces to evaluate.
samplingPercentage (float) -- [REQUIRED]
The percentage of agent traces to sample for evaluation, ranging from 0.01% to 100%.
filters (list) --
The list of filters that determine which agent traces should be included in the evaluation based on trace properties.
(dict) --
The filter that applies conditions to agent traces during online evaluation to determine which traces should be evaluated.
key (string) -- [REQUIRED]
The key or field name to filter on within the agent trace data.
operator (string) -- [REQUIRED]
The comparison operator to use for filtering.
value (dict) -- [REQUIRED]
The value to compare against using the specified operator.
stringValue (string) --
The string value for text-based filtering.
doubleValue (float) --
The numeric value for numerical filtering and comparisons.
booleanValue (boolean) --
The boolean value for true/false filtering conditions.
sessionConfig (dict) --
The session configuration that defines timeout settings for detecting when agent sessions are complete and ready for evaluation.
sessionTimeoutMinutes (integer) -- [REQUIRED]
The number of minutes of inactivity after which an agent session is considered complete and ready for evaluation. Default is 15 minutes.
dict
The updated data source configuration specifying CloudWatch log groups and service names to monitor.
cloudWatchLogs (dict) --
The CloudWatch logs configuration for reading agent traces from log groups.
logGroupNames (list) -- [REQUIRED]
The list of CloudWatch log group names to monitor for agent traces.
(string) --
serviceNames (list) -- [REQUIRED]
The list of service names to filter traces within the specified log groups. Used to identify relevant agent sessions.
(string) --
list
The updated list of evaluators to apply during online evaluation.
(dict) --
The reference to an evaluator used in online evaluation configurations, containing the evaluator identifier.
evaluatorId (string) --
The unique identifier of the evaluator. Can reference builtin evaluators (e.g., Builtin.Helpfulness) or custom evaluators.
list
The updated list of insight types to run against agent sessions.
(dict) --
A reference to an insight analysis to run against sessions.
insightId (string) -- [REQUIRED]
Canonical insight identifiers using the Builtin.Insight.* naming convention. Used by BatchEvaluate, InternalEvaluate, and ServiceEngineEvaluate flows.
dict
The updated clustering configuration for periodic batch evaluation.
frequencies (list) -- [REQUIRED]
The list of frequencies at which clustering batch evaluations are triggered.
(string) --
string
The updated Amazon Resource Name (ARN) of the IAM role used for evaluation execution.
string
The updated execution status to enable or disable the online evaluation.
dict
Response Syntax
{
'onlineEvaluationConfigArn': 'string',
'onlineEvaluationConfigId': 'string',
'updatedAt': datetime(2015, 1, 1),
'status': 'ACTIVE'|'CREATING'|'CREATE_FAILED'|'UPDATING'|'UPDATE_FAILED'|'DELETING'|'ERROR',
'executionStatus': 'ENABLED'|'DISABLED',
'failureReason': 'string'
}
Response Structure
(dict) --
onlineEvaluationConfigArn (string) --
The Amazon Resource Name (ARN) of the updated online evaluation configuration.
onlineEvaluationConfigId (string) --
The unique identifier of the updated online evaluation configuration.
updatedAt (datetime) --
The timestamp when the online evaluation configuration was last updated.
status (string) --
The status of the online evaluation configuration.
executionStatus (string) --
The execution status indicating whether the online evaluation is currently running.
failureReason (string) --
The reason for failure if the online evaluation configuration update or execution failed.