|
Today, we are 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 Amazon Bedrock features such as knowledge bases, agents, and guardrails.
Developers can now sign in to Bedrock Studio using their company's single sign-on credentials and start experimenting. Build, evaluate, and share your generated AI apps with a variety of top-performing models within Bedrock Studio. The user interface guides you through various steps to improve the model's response. Experiment with model configurations, securely integrate your company's data sources, tools, and APIs, and set guardrails. Collaborate with your team members to ideate, experiment, and improve your generative AI applications without requiring advanced machine learning (ML) expertise or access to the AWS Management Console.
Amazon Web Services (AWS) administrators can be confident that their developers will only have access to the functionality provided by Bedrock Studio and not broader access to AWS infrastructure and services.
Now, learn how to get started using Amazon Bedrock Studio.
Try using Amazon Bedrock Studio
As an AWS administrator, you must first create an Amazon Bedrock Studio workspace and then select and add the users you want to allow access to the workspace. Once the workspace is created, you can share the workspace URL with each user. Users with access can sign in to the workspace using single sign-on, create projects within the workspace, and start building generative AI applications.
Create an Amazon Bedrock Studio workspace
Go to the Amazon Bedrock console and select bedrock studio It's in the bottom left pane.
Before you create a workspace, you must use AWS IAM Identity Center to set up and secure single sign-on integration with your identity provider (IdP). For more information about how to configure 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, we used the default IAM Identity Center directory to configure user access.
Then select Create a workspaceenter your workspace details, and create the required AWS Identity and Access Management (IAM) role.
Optionally, you can also select default generative AI models and embedded models for your workspace.Once done, please select create.
Next, select the workspace you created.
Then select User management and Add users or groups Click to select the users you want to allow access to this workspace.
Back overview Click the tab to Bedrock Studio URL and share it with your users.
Build generative AI applications using Amazon Bedrock Studio
Builders can now navigate to the provided Bedrock Studio URL and sign in using their single sign-on user credentials. Welcome to Amazon Bedrock Studio! Learn how to choose from industry-leading FMs, bring your own data, use functions to make API calls, and use guardrails to secure your applications.
Choose from multiple industry-leading FMs
by choosing exploreyou can start selecting available FMs and explore the model using natural language prompts.
if you choose buildNow you can start building generative AI applications in playground mode, experimenting with model configurations, iterating through system prompts to define application behavior, and prototyping new features.
bring your own data
Bedrock Studio allows you to securely bring your own data and customize your applications by providing a single file or choosing a knowledge base created with Amazon Bedrock.
Make API calls using functions to make model responses more relevant
Function calls allow FM to dynamically access and include external data or functionality when responding to prompts. The model determines which functions should be called based on the OpenAPI schema provided.
Functions allow you to include information in the response that the model does not have direct access to or prior knowledge about. For example, functions allow a model to retrieve current weather conditions and include them in the response, even if the model itself does not store that information.
Protect your applications with Guardrails for Amazon Bedrock
By implementing safeguards tailored to your use case and responsible AI policies, you can create guardrails to facilitate secure interactions between users and generative AI applications.
When you create an application in Amazon Bedrock Studio, corresponding management resources such as knowledge bases, agents, and guardrails are automatically deployed to your AWS account. You can access these resources for downstream applications using the Amazon Bedrock API.
This is a short demo video of Amazon Bedrock Studio created by my colleague Banjo Obayomi.
Participate in preview
Amazon Bedrock Studio is currently available in public preview in the AWS Regions US East (N. Virginia) and US West (Oregon). For more information, please visit the Amazon Bedrock Studio page and user guide.
Try Amazon Bedrock Studio today and let us know what you think. Please submit feedback to AWS re:Post on Amazon Bedrock or through your regular AWS contacts, and join the Generate AI Builders community at community.aws.
— Antie
