AWS recently announced Amazon Bedrock Studio, a web interface for developers to collaborate and build generative AI applications. Currently in public preview, this rapid prototyping environment provides access to multiple underlying models, knowledge bases, agents, and guardrails.
The Bedrock Studio interface guides developers through various steps to improve model responsiveness, experiment with model settings, tools, APIs, and set up guardrails. AWS administrators can configure one or more Amazon Bedrock Studio workspaces for their organization in the Bedrock management console and grant permissions to individuals and groups.
Source: AWS Blog
Antje Barth, Principal Developer Advocate at AWS, explains how to get started with Amazon Bedrock Studio.
An AWS administrator must first create an Amazon Bedrock Studio workspace and then select and add users who should have access to the workspace. Once the workspace is created, the workspace URL can be shared with the respective users. Users with access can sign in to the workspace using single sign-on, create projects within the workspace, and start building generative AI applications.
As with similar managed services like Amazon SageMaker Studio, developers only have access to the features the platform provides, not the AWS console, infrastructure, or services.
When you create an application in Amazon Bedrock Studio, the corresponding managed resources such as knowledge bases, agents, and guardrails are automatically deployed into your AWS account. You can access these resources in your downstream applications using the Amazon Bedrock APIs.
Source: AWS Blog
Amazon Bedrock Studio supports features such as agents, multiple Foundation Models (FM), and a range of tools. The knowledge base implements Search Augmentation Generation (RAG) and provides responses with citations, allowing users to verify source text to ensure factual accuracy. Guardrails allow developers to implement safeguards in their generative AI applications based on specific use cases and AI policies.
In her post, “A First Look at the New Amazon Bedrock Studio,” Monica Colangelo, Principal Cloud Architect at NTT DATA, highlights some of the limitations of the preview, including the requirement that AWS IAM Identity Center be configured in the same region where Bedrock Studio is currently available. She writes:
While the features in Amazon Bedrock Studio are not entirely new and have been available through the Amazon Bedrock service for some time, the real value proposition is the seamless playground environment where users can try out all these features simultaneously. This integrated approach significantly lowers the barrier to entry.
There is no additional cost for Bedrock Studio; customers pay only for what they use with Bedrock. Corey Quinn, Chief Cloud Economist at The Duckbill Group, said:
I wonder if Bedrock Canvas will be next. SageMaker did it. Those thieves still haven't paid me the $260 credit because of their predatory pricing model.
Jeremy Daly, CEO and founder of Ampt, wrote:
Some are getting frighteningly good.
Banjo Obayomi, Senior Developer Advocate at AWS, created a demo video to show how the new workspaces work: Bedrock Studio is currently available as a public preview in only two US regions: Northern Virginia and Oregon.
