Administer Amazon Bedrock Studio - Amazon Bedrock
Amazon Bedrock Studio and Amazon DataZone

Administer Amazon Bedrock Studio

Amazon Bedrock Studio, renamed to Amazon Bedrock IDE, is now available in Amazon SageMaker Unified Studio. Amazon Bedrock Studio will be available until February 28, 2025. You may access existing workspaces in this previous version through February 28, 2025, but you may not create new workspaces. To access the enhanced GA version of Amazon Bedrock Studio with additional features and capabilities, you can create a new Amazon SageMaker Unified Studio domain. To learn about Amazon Bedrock Studio IDE, see the documentation.

Amazon Bedrock Studio is a web application that lets users in your organization easily experiment with Amazon Bedrock models and build applications, without having to use an AWS account. It also avoids the complexity of your users having to set up and use a developer environment. For more information, see the Amazon Bedrock Studio user guide.

To enable Bedrock Studio for your users, you use the Amazon Bedrock console to create a Bedrock Studio workspace and invite users as members to that workspace. Within the workspace, users create projects in which they can experiment with Amazon Bedrock models and features, such as Knowledge Bases and guardrails.

As part of granting user access to Amazon Bedrock Studio, you need to set up Single Sign On (SSO) integration with IAM Identity Center and your company's Identity Provider (IDP). Workspace members can be users or groups of users in your organization.

Your users sign in to Amazon Bedrock Studio by using a link that you send to them.

You need permissions to administer Bedrock Studio workspaces. For more information, see Identity-based policy examples for Amazon Bedrock Studio.

Amazon Bedrock IDE is supported in the following Regions (for more information about Regions supported in Amazon Bedrock see Amazon Bedrock endpoints and quotas):

  • US East (N. Virginia)

  • US West (Oregon)

  • Asia Pacific (Tokyo)

  • Asia Pacific (Singapore)

  • Asia Pacific (Sydney)

  • Europe (Frankfurt)

  • Europe (Ireland)

Amazon Bedrock IDE is supported for the following foundation models (to see which Regions support each model, refer to Supported foundation models in Amazon Bedrock):

  • AI21 Labs Jamba 1.5 Large

  • AI21 Labs Jamba 1.5 Mini

  • AI21 Labs Jamba-Instruct

  • AI21 Labs Jurassic-2 Mid

  • AI21 Labs Jurassic-2 Ultra

  • Amazon Titan Embeddings G1 - Text

  • Amazon Titan Image Generator G1 v2

  • Amazon Titan Image Generator G1

  • Amazon Titan Text Embeddings V2

  • Amazon Titan Text G1 - Express

  • Amazon Titan Text G1 - Lite

  • Amazon Titan Text G1 - Premier

  • Anthropic Anthropic Claude 2.1

  • Anthropic Anthropic Claude 2

  • Anthropic Claude 3 Haiku

  • Anthropic Claude 3 Opus

  • Anthropic Claude 3 Sonnet

  • Anthropic Claude 3.5 Haiku

  • Anthropic Claude 3.5 Sonnet v2

  • Anthropic Claude 3.5 Sonnet

  • Cohere Command Light

  • Cohere Command R+

  • Cohere Command R

  • Cohere Command

  • Cohere Embed English

  • Cohere Embed Multilingual

  • Meta Llama 3 70B Instruct

  • Meta Llama 3 8B Instruct

  • Meta Llama 3.1 405B Instruct

  • Meta Llama 3.1 70B Instruct

  • Meta Llama 3.1 8B Instruct

  • Meta Llama 3.2 11B Instruct

  • Meta Llama 3.2 1B Instruct

  • Meta Llama 3.2 3B Instruct

  • Meta Llama 3.2 90B Instruct

  • Mistral AI Mistral 7B Instruct

  • Mistral AI Mistral Large (24.02)

  • Mistral AI Mistral Large (24.07)

  • Mistral AI Mistral Small (24.02)

  • Mistral AI Mixtral 8x7B Instruct

  • Stability AI SD3 Large 1.0

  • Stability AI SDXL 1.0

  • Stability AI Stable Image Core 1.0

  • Stability AI Stable Image Ultra 1.0

Topics

Amazon Bedrock Studio and Amazon DataZone

Amazon Bedrock uses resources created in Amazon DataZone to integrate with AWS IAM Identity Center, and to provide a secure environment for builders to log in and develop their apps. When an account administrator creates an Amazon Bedrock Studio workspace, an Amazon DataZone domain is created in your AWS account. We recommend that you manage the workspaces you create through the Amazon Bedrock console and not by directly modifying the Amazon DataZone domain.

When builders use Amazon Bedrock Studio, the projects, apps, and components they create are built using resources created in your AWS account. The name and description of projects, apps, or components are visible to all members of the Amazon Bedrock Studio workspace. We recommend that you don't store sensitive data in these two fields. Project-based access control ensures only authorized members of a project can edit the name, description, and other fields in the project.

The following is a list of the services where Amazon Bedrock Studio creates resources in your account:

  • AWS CloudFormation — Amazon Bedrock Studio uses CloudFormation stacks to securely create resources in your account. The CloudFormation stack for a resource (project, app, or component) is created when the resource is created in your Amazon Bedrock Studio workspace, and is deleted when the resource is deleted. All CloudFormation stacks are deployed in your account using the provisioning role you specify when you create the workspace. Cloudformation stacks are used to create and delete all of the other resources created by Amazon Bedrock Studio in your account.

  • AWS Identity and Access Management — dynamically creates IAM roles when Amazon Bedrock Studio resources are created. Some of the roles created are used internally by components, while some roles are used to let Amazon Bedrock Studio builders perform certain actions. Roles used by builders are scoped-down to the minimum resources necessary by default, and are created using the permission boundary AmazonDataZoneBedrockPermissionsBoundary in your AWS account.

  • Amazon S3 — Amazon Bedrock Studio creates a Amazon S3 bucket in your account for each project. The bucket stores app and component definitions, as well as data files you upload such Knowledge Base files or api schemas for functions.

  • Amazon Bedrock Studio — Apps and components in Amazon Bedrock Studio can create Amazon Bedrock agents, Knowledge Bases, and guardrails.

  • AWS Lambda — Lambda functions are used as part of the Amazon Bedrock Studio function and knowledgebase components.

  • AWS Secrets Manager — Amazon Bedrock Studio uses a Secrets Manager secret to store API credentials for the functions component.