Amazon Bedrock Studio

Amazon Bedrock Studio is a new SSO-enabled web interface that provides the easiest way for developers across an organization to experiment with large language models (LLMs) and other foundation models (FMs), collaborate on projects, and iterate on generative AI applications. It offers a rapid prototyping environment and streamlines access to multiple Foundation Models (FMs) and developer tools in Bedrock. To enable Bedrock Studio, AWS administrators can configure one or more workspaces for their organization in the AWS Management Console for Bedrock, and grant permissions to individuals or groups to use the workspace.

Developers at your organization can simply login to the Amazon Bedrock Studio web experience using their company credentials (SSO) and instantly start experimenting with Bedrock FMs and tools to build applications. With Bedrock Studio, developers get a secure environment outside of the AWS Management Console to leverage Bedrock tools such as Agents, Knowledge Bases, and Guardrails.

Amazon Bedrock Studio enables developers to make their generative AI apps more accurate and relevant in incremental steps. Developers can start with selecting an appropriate FM for their use case, then iteratively improve prompts to get more accurate responses from their app. They can then bring their own data to ground the app to get more relevant responses, and add APIs to get the most current responses. Bedrock Studio automatically deploys the relevant AWS resources (such as Knowledge Bases and Agents), taking away the complexity and simplifying the app building experience. Also, applications and data never leave the designated AWS account, providing a secure environment for enterprise use cases.

Amazon Bedrock Studio offers a collaborative development environment where teams can work together to ideate, experiment, and refine their generative AI applications. Developers can create projects, invite their colleagues, share applications and insights, and get instant feedback on their prototypes. Projects in Bedrock Studio provide access control to ensure only authorized members can access apps and resources within a project.

When developers create applications in Amazon Bedrock Studio, corresponding managed resources such as Knowledge Bases, Agents, and Guardrails are deployed automatically in their own AWS account. They do not have to worry about the underlying compute and storage infrastructure, these Bedrock resources are always ready to use and scale as needed. Moreover, these resources are easily accessible via the Bedrock API. This means you can seamlessly integrate the generative AI apps built in Bedrock Studio with their processes and workflows by using the Bedrock API.

Developers can create Guardrails and set content filters on both user input and model responses to ensure their app does not generate inappropriate output. They can set filtering levels across various categories and add denied topics to customize the Guardrail behavior to get the desired output from their apps.