AWS Debuts Bedrock Studio for 'Rapid AI Prototyping'

Amazon Web Services has released to public preview a "rapid prototyping environment" for developers looking to build generative AI applications.

Amazon Bedrock Studio is an easily accessible AI development environment that users can access via single sign-on (SSO), explained AWS' Antje Barth in a blog post.

"You can build applications using a wide array of top performing models, evaluate, and share your generative AI apps within Bedrock Studio," Barth wrote. "The user interface guides you through various steps to help improve a model's responses. You can experiment with model settings, and securely integrate your company data sources, tools, and APIs, and set guardrails. You can collaborate with team members to ideate, experiment, and refine your generative AI applications."

Developers don't need to have access to the AWS Management Console or even their company's broader AWS environment in order to use Bedrock Studio. AWS admins can choose which users have access to which Bedrock Studio workspace (after, of course, configuring SSO logistics via the AWS IAM Identity Center). Once that's done, said Barth, "[u]sers with access privileges can sign in to the workspace using single sign-on, create projects within their workspace, and start building generative AI applications."

Bedrock Studio gives developers access to a select number of foundation models with which to build their applications, including those from AI21, Stability AI, Cohere, Meta, Anthropic, Mistral and Amazon itself. Using natural language prompts, developers can experiment building with different types of models, tweak how their application behaves and add new features to it.

They can also import their own data for their application to use, whether it's data from a file or a knowledge base, or via an API call. In addition, developers can apply custom guardrails -- controls around AI misuse and harmful content -- to their application.

"When you create applications in Amazon Bedrock Studio, the corresponding managed resources such as knowledge bases, agents, and guardrails are automatically deployed in your AWS account," wrote Barth. "You can use the Amazon Bedrock API to access those resources in downstream applications."

The Bedrock Studio preview is available out of AWS' U.S. East and U.S. West regions. More information is available here.

About the Author

Gladys Rama (@GladysRama3) is the editorial director of Converge360.