Today, AWS announces the general availability of experimentation tools in AWS AppConfig, a new capability that enables you to run A/B tests and feature experiments without building or managing separate experimentation infrastructure. Built on 25+ years of Amazon experimentation best practices, AWS AppConfig experimentation tools use AI-driven guidance to help you build robust experiments while providing exposure control and locked treatment allocations so you can make confident, data-driven decisions about what to ship to your customers.

Using AWS AppConfig experimentation tools, you can run A/B tests and multivariate experiments across your application stack, from UI changes and recommendation algorithms to AI model selections and prompt experiments. Define feature variations, target granular audiences using a rule builder, and set traffic allocation percentages through the AWS Management Console, CLI, API, or AWS CDK. AI-assisted experiment design can validate your setup against Amazon’s best practices, helping you build experiments with sufficient statistical power. Customers set up and run the experiment in AWS AppConfig, and then analyze results using Amazon CloudWatch or existing analytics tools. At the end of the experiment, you promote the winning treatment to production through a standard AWS AppConfig safe rollout. Experiments work across workloads on Amazon EC2, AWS Lambda, Amazon ECS, Amazon EKS, and on-premises servers through AWS AppConfig Agent.