bedrockagentcore_create_ab_test: Creates an A/B test for comparing agent configurations

In paws.machine.learning: 'Amazon Web Services' Machine Learning Services

Creates an A/B test for comparing agent configurations

Description

Creates an A/B test for comparing agent configurations. A/B tests split traffic between a control variant and a treatment variant through a gateway, then evaluate performance using online evaluation configurations to determine which variant performs better.

See https://www.paws-r-sdk.com/docs/bedrockagentcore_create_ab_test/ for full documentation.

Usage

bedrockagentcore_create_ab_test(
  name,
  description = NULL,
  gatewayArn,
  variants,
  gatewayFilter = NULL,
  evaluationConfig,
  roleArn,
  enableOnCreate = NULL,
  clientToken = NULL
)

Arguments

name	[required] The name of the A/B test. Must be unique within your account.
description	The description of the A/B test.
gatewayArn	[required] The Amazon Resource Name (ARN) of the gateway to use for traffic splitting.
variants	[required] The list of variants for the A/B test. Must contain exactly two variants: a control (C) and a treatment (T1), each with a configuration bundle or target reference and a traffic weight.
gatewayFilter	Optional filter to restrict which gateway target paths are included in the A/B test.
evaluationConfig	[required] The evaluation configuration specifying which online evaluation configurations to use for measuring variant performance.
roleArn	[required] The IAM role ARN that grants permissions for the A/B test to access gateway and evaluation resources.
enableOnCreate	Whether to enable the A/B test immediately upon creation. If true, traffic splitting begins automatically.
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.

paws.machine.learning documentation built on May 31, 2026, 1:07 a.m.