Amazon Bedrock AgentCore

2026/08/11 - Amazon Bedrock AgentCore - 2 updated api methods

Changes  Adding online eval arn as input for recommendation API

GetRecommendation (updated) Link ¶
Changes (response)
{'recommendationConfig': {'systemPromptRecommendationConfig': {'agentTraces': {'onlineEvaluation': {'endTime': 'timestamp',
                                                                                                    'onlineEvaluationConfigArn': 'string',
                                                                                                    'startTime': 'timestamp'}}},
                          'toolDescriptionRecommendationConfig': {'agentTraces': {'onlineEvaluation': {'endTime': 'timestamp',
                                                                                                       'onlineEvaluationConfigArn': 'string',
                                                                                                       'startTime': 'timestamp'}}}}}

Retrieves detailed information about a recommendation, including its configuration, status, and results.

See also: AWS API Documentation

Request Syntax

client.get_recommendation(
    recommendationId='string'
)
type recommendationId:

string

param recommendationId:

[REQUIRED]

The unique identifier of the recommendation to retrieve.

rtype:

dict

returns:

Response Syntax

{
    'recommendationId': 'string',
    'recommendationArn': 'string',
    'name': 'string',
    'description': 'string',
    'type': 'SYSTEM_PROMPT_RECOMMENDATION'|'TOOL_DESCRIPTION_RECOMMENDATION',
    'recommendationConfig': {
        'systemPromptRecommendationConfig': {
            'systemPrompt': {
                'text': 'string',
                'configurationBundle': {
                    'bundleArn': 'string',
                    'versionId': 'string',
                    'systemPromptJsonPath': 'string'
                }
            },
            'agentTraces': {
                'sessionSpans': [
                    {...}|[...]|123|123.4|'string'|True|None,
                ],
                'cloudwatchLogs': {
                    'logGroupArns': [
                        'string',
                    ],
                    'serviceNames': [
                        'string',
                    ],
                    'startTime': datetime(2015, 1, 1),
                    'endTime': datetime(2015, 1, 1),
                    'rule': {
                        'filters': [
                            {
                                'key': 'string',
                                'operator': 'Equals'|'NotEquals'|'GreaterThan'|'LessThan'|'GreaterThanOrEqual'|'LessThanOrEqual'|'Contains'|'NotContains',
                                'value': {
                                    'stringValue': 'string',
                                    'doubleValue': 123.0,
                                    'booleanValue': True|False
                                }
                            },
                        ]
                    }
                },
                'batchEvaluation': {
                    'batchEvaluationArn': 'string'
                },
                'onlineEvaluation': {
                    'onlineEvaluationConfigArn': 'string',
                    'startTime': datetime(2015, 1, 1),
                    'endTime': datetime(2015, 1, 1)
                }
            },
            'evaluationConfig': {
                'evaluators': [
                    {
                        'evaluatorArn': 'string'
                    },
                ]
            }
        },
        'toolDescriptionRecommendationConfig': {
            'toolDescription': {
                'toolDescriptionText': {
                    'tools': [
                        {
                            'toolName': 'string',
                            'toolDescription': {
                                'text': 'string'
                            }
                        },
                    ]
                },
                'configurationBundle': {
                    'bundleArn': 'string',
                    'versionId': 'string',
                    'tools': [
                        {
                            'toolName': 'string',
                            'toolDescriptionJsonPath': 'string'
                        },
                    ]
                }
            },
            'agentTraces': {
                'sessionSpans': [
                    {...}|[...]|123|123.4|'string'|True|None,
                ],
                'cloudwatchLogs': {
                    'logGroupArns': [
                        'string',
                    ],
                    'serviceNames': [
                        'string',
                    ],
                    'startTime': datetime(2015, 1, 1),
                    'endTime': datetime(2015, 1, 1),
                    'rule': {
                        'filters': [
                            {
                                'key': 'string',
                                'operator': 'Equals'|'NotEquals'|'GreaterThan'|'LessThan'|'GreaterThanOrEqual'|'LessThanOrEqual'|'Contains'|'NotContains',
                                'value': {
                                    'stringValue': 'string',
                                    'doubleValue': 123.0,
                                    'booleanValue': True|False
                                }
                            },
                        ]
                    }
                },
                'batchEvaluation': {
                    'batchEvaluationArn': 'string'
                },
                'onlineEvaluation': {
                    'onlineEvaluationConfigArn': 'string',
                    'startTime': datetime(2015, 1, 1),
                    'endTime': datetime(2015, 1, 1)
                }
            }
        }
    },
    'status': 'PENDING'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'DELETING',
    'createdAt': datetime(2015, 1, 1),
    'updatedAt': datetime(2015, 1, 1),
    'recommendationResult': {
        'systemPromptRecommendationResult': {
            'recommendedSystemPrompt': 'string',
            'configurationBundle': {
                'bundleArn': 'string',
                'versionId': 'string'
            },
            'explanation': 'string',
            'errorCode': 'string',
            'errorMessage': 'string'
        },
        'toolDescriptionRecommendationResult': {
            'tools': [
                {
                    'toolName': 'string',
                    'recommendedToolDescription': 'string',
                    'explanation': 'string'
                },
            ],
            'configurationBundle': {
                'bundleArn': 'string',
                'versionId': 'string'
            },
            'errorCode': 'string',
            'errorMessage': 'string'
        }
    },
    'kmsKeyArn': 'string'
}

Response Structure

  • (dict) --

    • recommendationId (string) --

      The unique identifier of the recommendation.

    • recommendationArn (string) --

      The Amazon Resource Name (ARN) of the recommendation.

    • name (string) --

      The name of the recommendation.

    • description (string) --

      The description of the recommendation.

    • type (string) --

      The type of recommendation.

    • recommendationConfig (dict) --

      The configuration for the recommendation.

      • systemPromptRecommendationConfig (dict) --

        The configuration for a system prompt recommendation.

        • systemPrompt (dict) --

          The current system prompt to optimize.

          • text (string) --

            The system prompt text provided inline.

          • configurationBundle (dict) --

            The system prompt sourced from a configuration bundle version.

            • bundleArn (string) --

              The Amazon Resource Name (ARN) of the configuration bundle.

            • versionId (string) --

              The version identifier of the configuration bundle.

            • systemPromptJsonPath (string) --

              The JSON path within the configuration bundle that contains the system prompt.

        • agentTraces (dict) --

          The agent traces to analyze for generating recommendations.

          • sessionSpans (list) --

            Agent traces provided as inline session spans in OpenTelemetry format.

            • (:ref:`document<document>`) --

          • cloudwatchLogs (dict) --

            Agent traces read from CloudWatch Logs.

            • logGroupArns (list) --

              The list of CloudWatch log group ARNs to read agent traces from.

              • (string) --

            • serviceNames (list) --

              The list of service names to filter traces within the specified log groups.

              • (string) --

            • startTime (datetime) --

              The start time of the time range to read traces from.

            • endTime (datetime) --

              The end time of the time range to read traces from.

            • rule (dict) --

              Optional rule configuration for filtering traces.

              • filters (list) --

                The list of filters to apply when reading agent traces.

                • (dict) --

                  A filter for narrowing down agent traces from CloudWatch Logs based on key-value comparisons.

                  • 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) --

                      A string value for text-based filtering.

                    • doubleValue (float) --

                      A numeric value for numerical filtering and comparisons.

                    • booleanValue (boolean) --

                      A boolean value for true/false filtering conditions.

          • batchEvaluation (dict) --

            Use a completed batch evaluation as the source of agent traces.

            • batchEvaluationArn (string) --

              The ARN of the completed batch evaluation to use as the trace source.

          • onlineEvaluation (dict) --

            Agent traces from an online evaluation configuration over a specified time range.

            • onlineEvaluationConfigArn (string) --

              The ARN of the online evaluation configuration to reuse sessions from.

            • startTime (datetime) --

              The start time of the time range. Only sessions evaluated at or after this timestamp are included.

            • endTime (datetime) --

              The end time of the time range. Only sessions evaluated before this timestamp are included.

        • evaluationConfig (dict) --

          The evaluation configuration specifying which evaluator to use for assessing recommendation quality.

          • evaluators (list) --

            The list of evaluators to use for assessing recommendation quality.

            • (dict) --

              A reference to an evaluator used for recommendation assessment.

              • evaluatorArn (string) --

                The Amazon Resource Name (ARN) of the evaluator.

      • toolDescriptionRecommendationConfig (dict) --

        The configuration for a tool description recommendation.

        • toolDescription (dict) --

          The current tool descriptions to optimize.

          • toolDescriptionText (dict) --

            Tool descriptions provided as inline text.

            • tools (list) --

              The list of tool descriptions to optimize.

              • (dict) --

                A tool description input containing the tool name and its current description.

                • toolName (string) --

                  The name of the tool.

                • toolDescription (dict) --

                  The current description of the tool to optimize.

                  • text (string) --

                    The tool description as inline text.

          • configurationBundle (dict) --

            Tool descriptions sourced from a configuration bundle version.

            • bundleArn (string) --

              The Amazon Resource Name (ARN) of the configuration bundle.

            • versionId (string) --

              The version identifier of the configuration bundle.

            • tools (list) --

              The list of tool entries mapping tool names to their JSON paths within the bundle.

              • (dict) --

                Maps a tool name to its JSON path within a configuration bundle.

                • toolName (string) --

                  The name of the tool.

                • toolDescriptionJsonPath (string) --

                  The JSON path within the configuration bundle's components that contains the tool description.

        • agentTraces (dict) --

          The agent traces to analyze for generating tool description recommendations.

          • sessionSpans (list) --

            Agent traces provided as inline session spans in OpenTelemetry format.

            • (:ref:`document<document>`) --

          • cloudwatchLogs (dict) --

            Agent traces read from CloudWatch Logs.

            • logGroupArns (list) --

              The list of CloudWatch log group ARNs to read agent traces from.

              • (string) --

            • serviceNames (list) --

              The list of service names to filter traces within the specified log groups.

              • (string) --

            • startTime (datetime) --

              The start time of the time range to read traces from.

            • endTime (datetime) --

              The end time of the time range to read traces from.

            • rule (dict) --

              Optional rule configuration for filtering traces.

              • filters (list) --

                The list of filters to apply when reading agent traces.

                • (dict) --

                  A filter for narrowing down agent traces from CloudWatch Logs based on key-value comparisons.

                  • 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) --

                      A string value for text-based filtering.

                    • doubleValue (float) --

                      A numeric value for numerical filtering and comparisons.

                    • booleanValue (boolean) --

                      A boolean value for true/false filtering conditions.

          • batchEvaluation (dict) --

            Use a completed batch evaluation as the source of agent traces.

            • batchEvaluationArn (string) --

              The ARN of the completed batch evaluation to use as the trace source.

          • onlineEvaluation (dict) --

            Agent traces from an online evaluation configuration over a specified time range.

            • onlineEvaluationConfigArn (string) --

              The ARN of the online evaluation configuration to reuse sessions from.

            • startTime (datetime) --

              The start time of the time range. Only sessions evaluated at or after this timestamp are included.

            • endTime (datetime) --

              The end time of the time range. Only sessions evaluated before this timestamp are included.

    • status (string) --

      The current status of the recommendation.

    • createdAt (datetime) --

      The timestamp when the recommendation was created.

    • updatedAt (datetime) --

      The timestamp when the recommendation was last updated.

    • recommendationResult (dict) --

      The result of the recommendation, containing the optimized system prompt or tool descriptions. Only present when the recommendation status is COMPLETED.

      • systemPromptRecommendationResult (dict) --

        The result of a system prompt recommendation.

        • recommendedSystemPrompt (string) --

          The optimized system prompt text generated by the recommendation.

        • configurationBundle (dict) --

          The configuration bundle containing the recommended system prompt, if the input was sourced from a configuration bundle.

          • bundleArn (string) --

            The Amazon Resource Name (ARN) of the configuration bundle.

          • versionId (string) --

            The version identifier of the configuration bundle containing the recommendation.

        • explanation (string) --

          An explanation of why the recommendation was generated and what patterns were identified in the agent traces.

        • errorCode (string) --

          The error code if the recommendation failed.

        • errorMessage (string) --

          The error message if the recommendation failed.

      • toolDescriptionRecommendationResult (dict) --

        The result of a tool description recommendation.

        • tools (list) --

          The list of tools with their recommended descriptions.

          • (dict) --

            The output for a single tool description recommendation.

            • toolName (string) --

              The name of the tool.

            • recommendedToolDescription (string) --

              The optimized tool description text generated by the recommendation.

            • explanation (string) --

              An explanation of why the recommendation was generated for this tool and what patterns were identified in the agent traces.

        • configurationBundle (dict) --

          The configuration bundle containing the recommended tool descriptions, if the input was sourced from a configuration bundle.

          • bundleArn (string) --

            The Amazon Resource Name (ARN) of the configuration bundle.

          • versionId (string) --

            The version identifier of the configuration bundle containing the recommendation.

        • errorCode (string) --

          The error code if the recommendation failed.

        • errorMessage (string) --

          The error message if the recommendation failed.

    • kmsKeyArn (string) --

      The ARN of the KMS key used to encrypt recommendation data.

StartRecommendation (updated) Link ¶
Changes (both)
{'recommendationConfig': {'systemPromptRecommendationConfig': {'agentTraces': {'onlineEvaluation': {'endTime': 'timestamp',
                                                                                                    'onlineEvaluationConfigArn': 'string',
                                                                                                    'startTime': 'timestamp'}}},
                          'toolDescriptionRecommendationConfig': {'agentTraces': {'onlineEvaluation': {'endTime': 'timestamp',
                                                                                                       'onlineEvaluationConfigArn': 'string',
                                                                                                       'startTime': 'timestamp'}}}}}

Starts a recommendation job that analyzes agent traces and generates optimization suggestions for system prompts or tool descriptions to improve agent performance.

See also: AWS API Documentation

Request Syntax

client.start_recommendation(
    name='string',
    description='string',
    type='SYSTEM_PROMPT_RECOMMENDATION'|'TOOL_DESCRIPTION_RECOMMENDATION',
    recommendationConfig={
        'systemPromptRecommendationConfig': {
            'systemPrompt': {
                'text': 'string',
                'configurationBundle': {
                    'bundleArn': 'string',
                    'versionId': 'string',
                    'systemPromptJsonPath': 'string'
                }
            },
            'agentTraces': {
                'sessionSpans': [
                    {...}|[...]|123|123.4|'string'|True|None,
                ],
                'cloudwatchLogs': {
                    'logGroupArns': [
                        'string',
                    ],
                    'serviceNames': [
                        'string',
                    ],
                    'startTime': datetime(2015, 1, 1),
                    'endTime': datetime(2015, 1, 1),
                    'rule': {
                        'filters': [
                            {
                                'key': 'string',
                                'operator': 'Equals'|'NotEquals'|'GreaterThan'|'LessThan'|'GreaterThanOrEqual'|'LessThanOrEqual'|'Contains'|'NotContains',
                                'value': {
                                    'stringValue': 'string',
                                    'doubleValue': 123.0,
                                    'booleanValue': True|False
                                }
                            },
                        ]
                    }
                },
                'batchEvaluation': {
                    'batchEvaluationArn': 'string'
                },
                'onlineEvaluation': {
                    'onlineEvaluationConfigArn': 'string',
                    'startTime': datetime(2015, 1, 1),
                    'endTime': datetime(2015, 1, 1)
                }
            },
            'evaluationConfig': {
                'evaluators': [
                    {
                        'evaluatorArn': 'string'
                    },
                ]
            }
        },
        'toolDescriptionRecommendationConfig': {
            'toolDescription': {
                'toolDescriptionText': {
                    'tools': [
                        {
                            'toolName': 'string',
                            'toolDescription': {
                                'text': 'string'
                            }
                        },
                    ]
                },
                'configurationBundle': {
                    'bundleArn': 'string',
                    'versionId': 'string',
                    'tools': [
                        {
                            'toolName': 'string',
                            'toolDescriptionJsonPath': 'string'
                        },
                    ]
                }
            },
            'agentTraces': {
                'sessionSpans': [
                    {...}|[...]|123|123.4|'string'|True|None,
                ],
                'cloudwatchLogs': {
                    'logGroupArns': [
                        'string',
                    ],
                    'serviceNames': [
                        'string',
                    ],
                    'startTime': datetime(2015, 1, 1),
                    'endTime': datetime(2015, 1, 1),
                    'rule': {
                        'filters': [
                            {
                                'key': 'string',
                                'operator': 'Equals'|'NotEquals'|'GreaterThan'|'LessThan'|'GreaterThanOrEqual'|'LessThanOrEqual'|'Contains'|'NotContains',
                                'value': {
                                    'stringValue': 'string',
                                    'doubleValue': 123.0,
                                    'booleanValue': True|False
                                }
                            },
                        ]
                    }
                },
                'batchEvaluation': {
                    'batchEvaluationArn': 'string'
                },
                'onlineEvaluation': {
                    'onlineEvaluationConfigArn': 'string',
                    'startTime': datetime(2015, 1, 1),
                    'endTime': datetime(2015, 1, 1)
                }
            }
        }
    },
    kmsKeyArn='string',
    clientToken='string',
    tags={
        'string': 'string'
    }
)
type name:

string

param name:

[REQUIRED]

The name of the recommendation. Must be unique within your account.

type description:

string

param description:

The description of the recommendation.

type type:

string

param type:

[REQUIRED]

The type of recommendation to generate. Valid values are SYSTEM_PROMPT_RECOMMENDATION for system prompt optimization or TOOL_DESCRIPTION_RECOMMENDATION for tool description optimization.

type recommendationConfig:

dict

param recommendationConfig:

[REQUIRED]

The configuration for the recommendation, including the input to optimize, agent traces to analyze, and evaluation settings.

  • systemPromptRecommendationConfig (dict) --

    The configuration for a system prompt recommendation.

    • systemPrompt (dict) -- [REQUIRED]

      The current system prompt to optimize.

      • text (string) --

        The system prompt text provided inline.

      • configurationBundle (dict) --

        The system prompt sourced from a configuration bundle version.

        • bundleArn (string) -- [REQUIRED]

          The Amazon Resource Name (ARN) of the configuration bundle.

        • versionId (string) -- [REQUIRED]

          The version identifier of the configuration bundle.

        • systemPromptJsonPath (string) -- [REQUIRED]

          The JSON path within the configuration bundle that contains the system prompt.

    • agentTraces (dict) -- [REQUIRED]

      The agent traces to analyze for generating recommendations.

      • sessionSpans (list) --

        Agent traces provided as inline session spans in OpenTelemetry format.

        • (:ref:`document<document>`) --

      • cloudwatchLogs (dict) --

        Agent traces read from CloudWatch Logs.

        • logGroupArns (list) -- [REQUIRED]

          The list of CloudWatch log group ARNs to read agent traces from.

          • (string) --

        • serviceNames (list) -- [REQUIRED]

          The list of service names to filter traces within the specified log groups.

          • (string) --

        • startTime (datetime) -- [REQUIRED]

          The start time of the time range to read traces from.

        • endTime (datetime) -- [REQUIRED]

          The end time of the time range to read traces from.

        • rule (dict) --

          Optional rule configuration for filtering traces.

          • filters (list) --

            The list of filters to apply when reading agent traces.

            • (dict) --

              A filter for narrowing down agent traces from CloudWatch Logs based on key-value comparisons.

              • 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) --

                  A string value for text-based filtering.

                • doubleValue (float) --

                  A numeric value for numerical filtering and comparisons.

                • booleanValue (boolean) --

                  A boolean value for true/false filtering conditions.

      • batchEvaluation (dict) --

        Use a completed batch evaluation as the source of agent traces.

        • batchEvaluationArn (string) -- [REQUIRED]

          The ARN of the completed batch evaluation to use as the trace source.

      • onlineEvaluation (dict) --

        Agent traces from an online evaluation configuration over a specified time range.

        • onlineEvaluationConfigArn (string) -- [REQUIRED]

          The ARN of the online evaluation configuration to reuse sessions from.

        • startTime (datetime) -- [REQUIRED]

          The start time of the time range. Only sessions evaluated at or after this timestamp are included.

        • endTime (datetime) -- [REQUIRED]

          The end time of the time range. Only sessions evaluated before this timestamp are included.

    • evaluationConfig (dict) --

      The evaluation configuration specifying which evaluator to use for assessing recommendation quality.

      • evaluators (list) -- [REQUIRED]

        The list of evaluators to use for assessing recommendation quality.

        • (dict) --

          A reference to an evaluator used for recommendation assessment.

          • evaluatorArn (string) -- [REQUIRED]

            The Amazon Resource Name (ARN) of the evaluator.

  • toolDescriptionRecommendationConfig (dict) --

    The configuration for a tool description recommendation.

    • toolDescription (dict) -- [REQUIRED]

      The current tool descriptions to optimize.

      • toolDescriptionText (dict) --

        Tool descriptions provided as inline text.

        • tools (list) -- [REQUIRED]

          The list of tool descriptions to optimize.

          • (dict) --

            A tool description input containing the tool name and its current description.

            • toolName (string) -- [REQUIRED]

              The name of the tool.

            • toolDescription (dict) -- [REQUIRED]

              The current description of the tool to optimize.

              • text (string) --

                The tool description as inline text.

      • configurationBundle (dict) --

        Tool descriptions sourced from a configuration bundle version.

        • bundleArn (string) -- [REQUIRED]

          The Amazon Resource Name (ARN) of the configuration bundle.

        • versionId (string) -- [REQUIRED]

          The version identifier of the configuration bundle.

        • tools (list) -- [REQUIRED]

          The list of tool entries mapping tool names to their JSON paths within the bundle.

          • (dict) --

            Maps a tool name to its JSON path within a configuration bundle.

            • toolName (string) -- [REQUIRED]

              The name of the tool.

            • toolDescriptionJsonPath (string) -- [REQUIRED]

              The JSON path within the configuration bundle's components that contains the tool description.

    • agentTraces (dict) -- [REQUIRED]

      The agent traces to analyze for generating tool description recommendations.

      • sessionSpans (list) --

        Agent traces provided as inline session spans in OpenTelemetry format.

        • (:ref:`document<document>`) --

      • cloudwatchLogs (dict) --

        Agent traces read from CloudWatch Logs.

        • logGroupArns (list) -- [REQUIRED]

          The list of CloudWatch log group ARNs to read agent traces from.

          • (string) --

        • serviceNames (list) -- [REQUIRED]

          The list of service names to filter traces within the specified log groups.

          • (string) --

        • startTime (datetime) -- [REQUIRED]

          The start time of the time range to read traces from.

        • endTime (datetime) -- [REQUIRED]

          The end time of the time range to read traces from.

        • rule (dict) --

          Optional rule configuration for filtering traces.

          • filters (list) --

            The list of filters to apply when reading agent traces.

            • (dict) --

              A filter for narrowing down agent traces from CloudWatch Logs based on key-value comparisons.

              • 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) --

                  A string value for text-based filtering.

                • doubleValue (float) --

                  A numeric value for numerical filtering and comparisons.

                • booleanValue (boolean) --

                  A boolean value for true/false filtering conditions.

      • batchEvaluation (dict) --

        Use a completed batch evaluation as the source of agent traces.

        • batchEvaluationArn (string) -- [REQUIRED]

          The ARN of the completed batch evaluation to use as the trace source.

      • onlineEvaluation (dict) --

        Agent traces from an online evaluation configuration over a specified time range.

        • onlineEvaluationConfigArn (string) -- [REQUIRED]

          The ARN of the online evaluation configuration to reuse sessions from.

        • startTime (datetime) -- [REQUIRED]

          The start time of the time range. Only sessions evaluated at or after this timestamp are included.

        • endTime (datetime) -- [REQUIRED]

          The end time of the time range. Only sessions evaluated before this timestamp are included.

type kmsKeyArn:

string

param kmsKeyArn:

The ARN of the KMS key used to encrypt recommendation data. If provided, customer data is encrypted at rest with the specified key.

type clientToken:

string

param clientToken:

A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, the service ignores the request, but does not return an error.

This field is autopopulated if not provided.

type tags:

dict

param tags:

A map of tag keys and values to associate with the recommendation.

  • (string) --

    • (string) --

rtype:

dict

returns:

Response Syntax

{
    'recommendationId': 'string',
    'recommendationArn': 'string',
    'name': 'string',
    'description': 'string',
    'type': 'SYSTEM_PROMPT_RECOMMENDATION'|'TOOL_DESCRIPTION_RECOMMENDATION',
    'recommendationConfig': {
        'systemPromptRecommendationConfig': {
            'systemPrompt': {
                'text': 'string',
                'configurationBundle': {
                    'bundleArn': 'string',
                    'versionId': 'string',
                    'systemPromptJsonPath': 'string'
                }
            },
            'agentTraces': {
                'sessionSpans': [
                    {...}|[...]|123|123.4|'string'|True|None,
                ],
                'cloudwatchLogs': {
                    'logGroupArns': [
                        'string',
                    ],
                    'serviceNames': [
                        'string',
                    ],
                    'startTime': datetime(2015, 1, 1),
                    'endTime': datetime(2015, 1, 1),
                    'rule': {
                        'filters': [
                            {
                                'key': 'string',
                                'operator': 'Equals'|'NotEquals'|'GreaterThan'|'LessThan'|'GreaterThanOrEqual'|'LessThanOrEqual'|'Contains'|'NotContains',
                                'value': {
                                    'stringValue': 'string',
                                    'doubleValue': 123.0,
                                    'booleanValue': True|False
                                }
                            },
                        ]
                    }
                },
                'batchEvaluation': {
                    'batchEvaluationArn': 'string'
                },
                'onlineEvaluation': {
                    'onlineEvaluationConfigArn': 'string',
                    'startTime': datetime(2015, 1, 1),
                    'endTime': datetime(2015, 1, 1)
                }
            },
            'evaluationConfig': {
                'evaluators': [
                    {
                        'evaluatorArn': 'string'
                    },
                ]
            }
        },
        'toolDescriptionRecommendationConfig': {
            'toolDescription': {
                'toolDescriptionText': {
                    'tools': [
                        {
                            'toolName': 'string',
                            'toolDescription': {
                                'text': 'string'
                            }
                        },
                    ]
                },
                'configurationBundle': {
                    'bundleArn': 'string',
                    'versionId': 'string',
                    'tools': [
                        {
                            'toolName': 'string',
                            'toolDescriptionJsonPath': 'string'
                        },
                    ]
                }
            },
            'agentTraces': {
                'sessionSpans': [
                    {...}|[...]|123|123.4|'string'|True|None,
                ],
                'cloudwatchLogs': {
                    'logGroupArns': [
                        'string',
                    ],
                    'serviceNames': [
                        'string',
                    ],
                    'startTime': datetime(2015, 1, 1),
                    'endTime': datetime(2015, 1, 1),
                    'rule': {
                        'filters': [
                            {
                                'key': 'string',
                                'operator': 'Equals'|'NotEquals'|'GreaterThan'|'LessThan'|'GreaterThanOrEqual'|'LessThanOrEqual'|'Contains'|'NotContains',
                                'value': {
                                    'stringValue': 'string',
                                    'doubleValue': 123.0,
                                    'booleanValue': True|False
                                }
                            },
                        ]
                    }
                },
                'batchEvaluation': {
                    'batchEvaluationArn': 'string'
                },
                'onlineEvaluation': {
                    'onlineEvaluationConfigArn': 'string',
                    'startTime': datetime(2015, 1, 1),
                    'endTime': datetime(2015, 1, 1)
                }
            }
        }
    },
    'status': 'PENDING'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'DELETING',
    'createdAt': datetime(2015, 1, 1),
    'updatedAt': datetime(2015, 1, 1)
}

Response Structure

  • (dict) --

    • recommendationId (string) --

      The unique identifier of the created recommendation.

    • recommendationArn (string) --

      The Amazon Resource Name (ARN) of the created recommendation.

    • name (string) --

      The name of the recommendation.

    • description (string) --

      The description of the recommendation.

    • type (string) --

      The type of recommendation.

    • recommendationConfig (dict) --

      The configuration for the recommendation.

      • systemPromptRecommendationConfig (dict) --

        The configuration for a system prompt recommendation.

        • systemPrompt (dict) --

          The current system prompt to optimize.

          • text (string) --

            The system prompt text provided inline.

          • configurationBundle (dict) --

            The system prompt sourced from a configuration bundle version.

            • bundleArn (string) --

              The Amazon Resource Name (ARN) of the configuration bundle.

            • versionId (string) --

              The version identifier of the configuration bundle.

            • systemPromptJsonPath (string) --

              The JSON path within the configuration bundle that contains the system prompt.

        • agentTraces (dict) --

          The agent traces to analyze for generating recommendations.

          • sessionSpans (list) --

            Agent traces provided as inline session spans in OpenTelemetry format.

            • (:ref:`document<document>`) --

          • cloudwatchLogs (dict) --

            Agent traces read from CloudWatch Logs.

            • logGroupArns (list) --

              The list of CloudWatch log group ARNs to read agent traces from.

              • (string) --

            • serviceNames (list) --

              The list of service names to filter traces within the specified log groups.

              • (string) --

            • startTime (datetime) --

              The start time of the time range to read traces from.

            • endTime (datetime) --

              The end time of the time range to read traces from.

            • rule (dict) --

              Optional rule configuration for filtering traces.

              • filters (list) --

                The list of filters to apply when reading agent traces.

                • (dict) --

                  A filter for narrowing down agent traces from CloudWatch Logs based on key-value comparisons.

                  • 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) --

                      A string value for text-based filtering.

                    • doubleValue (float) --

                      A numeric value for numerical filtering and comparisons.

                    • booleanValue (boolean) --

                      A boolean value for true/false filtering conditions.

          • batchEvaluation (dict) --

            Use a completed batch evaluation as the source of agent traces.

            • batchEvaluationArn (string) --

              The ARN of the completed batch evaluation to use as the trace source.

          • onlineEvaluation (dict) --

            Agent traces from an online evaluation configuration over a specified time range.

            • onlineEvaluationConfigArn (string) --

              The ARN of the online evaluation configuration to reuse sessions from.

            • startTime (datetime) --

              The start time of the time range. Only sessions evaluated at or after this timestamp are included.

            • endTime (datetime) --

              The end time of the time range. Only sessions evaluated before this timestamp are included.

        • evaluationConfig (dict) --

          The evaluation configuration specifying which evaluator to use for assessing recommendation quality.

          • evaluators (list) --

            The list of evaluators to use for assessing recommendation quality.

            • (dict) --

              A reference to an evaluator used for recommendation assessment.

              • evaluatorArn (string) --

                The Amazon Resource Name (ARN) of the evaluator.

      • toolDescriptionRecommendationConfig (dict) --

        The configuration for a tool description recommendation.

        • toolDescription (dict) --

          The current tool descriptions to optimize.

          • toolDescriptionText (dict) --

            Tool descriptions provided as inline text.

            • tools (list) --

              The list of tool descriptions to optimize.

              • (dict) --

                A tool description input containing the tool name and its current description.

                • toolName (string) --

                  The name of the tool.

                • toolDescription (dict) --

                  The current description of the tool to optimize.

                  • text (string) --

                    The tool description as inline text.

          • configurationBundle (dict) --

            Tool descriptions sourced from a configuration bundle version.

            • bundleArn (string) --

              The Amazon Resource Name (ARN) of the configuration bundle.

            • versionId (string) --

              The version identifier of the configuration bundle.

            • tools (list) --

              The list of tool entries mapping tool names to their JSON paths within the bundle.

              • (dict) --

                Maps a tool name to its JSON path within a configuration bundle.

                • toolName (string) --

                  The name of the tool.

                • toolDescriptionJsonPath (string) --

                  The JSON path within the configuration bundle's components that contains the tool description.

        • agentTraces (dict) --

          The agent traces to analyze for generating tool description recommendations.

          • sessionSpans (list) --

            Agent traces provided as inline session spans in OpenTelemetry format.

            • (:ref:`document<document>`) --

          • cloudwatchLogs (dict) --

            Agent traces read from CloudWatch Logs.

            • logGroupArns (list) --

              The list of CloudWatch log group ARNs to read agent traces from.

              • (string) --

            • serviceNames (list) --

              The list of service names to filter traces within the specified log groups.

              • (string) --

            • startTime (datetime) --

              The start time of the time range to read traces from.

            • endTime (datetime) --

              The end time of the time range to read traces from.

            • rule (dict) --

              Optional rule configuration for filtering traces.

              • filters (list) --

                The list of filters to apply when reading agent traces.

                • (dict) --

                  A filter for narrowing down agent traces from CloudWatch Logs based on key-value comparisons.

                  • 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) --

                      A string value for text-based filtering.

                    • doubleValue (float) --

                      A numeric value for numerical filtering and comparisons.

                    • booleanValue (boolean) --

                      A boolean value for true/false filtering conditions.

          • batchEvaluation (dict) --

            Use a completed batch evaluation as the source of agent traces.

            • batchEvaluationArn (string) --

              The ARN of the completed batch evaluation to use as the trace source.

          • onlineEvaluation (dict) --

            Agent traces from an online evaluation configuration over a specified time range.

            • onlineEvaluationConfigArn (string) --

              The ARN of the online evaluation configuration to reuse sessions from.

            • startTime (datetime) --

              The start time of the time range. Only sessions evaluated at or after this timestamp are included.

            • endTime (datetime) --

              The end time of the time range. Only sessions evaluated before this timestamp are included.

    • status (string) --

      The status of the recommendation.

    • createdAt (datetime) --

      The timestamp when the recommendation was created.

    • updatedAt (datetime) --

      The timestamp when the recommendation was last updated.