Today, we're introducing Amazon Bedrock Studio, a new web-based generative artificial intelligence (generative AI) development experience, in public preview. Amazon Bedrock Studio accelerates the development of generative AI applications by providing a rapid prototyping environment with key features of Amazon Bedrock, including knowledge bases, agents, and guardrails.
As a developer, you can now use your company's single sign-on credentials to sign in to Bedrock Studio and start experimenting. You can build applications, evaluate and share your creative AI apps using a wide array of high-performance models in Bedrock Studio. The user interface guides you through various steps to help improve the model's responses. You can experiment with model settings, and securely integrate your company's data sources, tools, and APIs, and set guardrails. You can collaborate with team members to ideate, experiment, and improve your generative AI applications—all without requiring advanced machine learning (ML) skills or access to the AWS Management Console.
As an Amazon Web Services (AWS) administrator, you can be confident that developers will only have access to the features provided by Bedrock Studio, and not broader access to AWS infrastructure and services.
Now, let me show you how to get started with Amazon Bedrock Studio.
Get started with Amazon Bedrock Studio.
As an AWS administrator, you first need to create an Amazon Bedrock Studio workspace, then select and add the users you want to grant access to the workspace. After the workspace is created, you can share the workspace URL with relevant users. Users with access privileges can sign in to a workspace using single sign-on, create projects within their workspace, and start building generative AI applications.
Create an Amazon Bedrock Studio workspace
Go to the Amazon Bedrock console and select Bedrock Studio On the bottom left pane.
Before creating a workspace, you need to configure and secure single sign-on integration with your identity provider (IdP) using AWS IAM Identity Center. For detailed instructions on configuring different IDPs, such as AWS Directory Service for Microsoft Active Directory, Microsoft Entra ID, or Okta, see the AWS IAM Identity Center User Guide. For this demo, I configured user access with the default IAM identity center directory.
Next, select Create a workspaceenter your workspace details, and create any desired AWS Identity and Access Management (IAM) roles.
If you want, you can also select default generative AI models and embedding models for the workspace. Once you're done, select to create.
Next, select the created workspace.
Then, select User management And Add users or groups. To select the users you want to give access to this workspace.
i back Overview tab, you can now copy. Bedrock Studio URL And share it with your customers.
Build creative AI applications using Amazon Bedrock Studio
As a builder, you can now visit the provided Bedrock Studio URL and sign in with your single sign-on user credentials. Welcome to Amazon Bedrock Studio! Let me show you how to choose from industry-leading FMs, fetch your data, use functions to make API calls, and protect your applications using guardrails.
Choose from a variety of industry leading FMs.
by choosing Explore.you can start selecting available FMs and search for models using natural language notation.
If you choose Build.you can start building generative AI applications in Playground mode, experiment with model configurations, iterate over system prompts to define your application's behavior, and prototype new features. are
Bring your data.
With Bedrock Studio, you can securely import your data to customize your application by providing a file or selecting a knowledge base created in Amazon Bedrock.
Use functions to make API calls and model responses more relevant.
A function call allows the FM to dynamically access and add external data or capabilities when responding to a prompt. The model determines which function it needs to call based on the OpenAPI schema you provide.
Functions enable the model to include information in its response that it does not have direct access to or prior knowledge of. For example, a function may allow the model to retrieve and include current weather conditions in its response, even though the model itself does not store that information.
Protect your applications using Guardrails for Amazon Bedrock.
You can build guardrails to promote safe interactions between users and your creative AI applications by implementing security measures tailored to your use cases and responsible AI policies.
When you build applications in Amazon Bedrock Studio, the associated managed resources such as knowledge bases, agents, and guardrails are automatically deployed to your AWS account. You can use the Amazon Bedrock API to access these resources in downstream applications.
Here's a short demo video of Amazon Bedrock Studio made by my colleague Banjo Obayomi.
Join the preview.
Amazon Bedrock Studio is available today in public preview in AWS Regions US East (N. Virginia) and US West (Oregon). To learn more, visit the Amazon Bedrock Studio page and user guide.
Try Amazon Bedrock Studio today and let us know what you think! Send feedback to AWS: Post to Amazon Bedrock or through your usual AWS contacts, and engage with the creative AI builder community at community.aws.
– Antje