AWS has recently announced Amazon Bedrock Studio, a web interface for developers to collaborate and build generative AI applications. Currently in public preview, the rapid prototyping environment provides access to multiple foundation models, knowledge bases, agents, and guardrails.
The Bedrock Studio interface guides developers through various steps to help improve a model’s responses, experiment with model settings, tools, and APIs, and set guardrails. AWS administrators can configure one or more Amazon Bedrock Studio workspaces for an organization in the Management Console for Bedrock 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:
As an AWS administrator, you first need to create an Amazon Bedrock Studio workspace, then select and add users you want to give access to the workspace. Once the workspace is created, you can share the workspace URL with the respective users. Users with access privileges can sign in to the workspace using single sign-on, create projects within their workspace, and start building generative AI applications.
As with similar managed services like Amazon SageMaker Studio, developers will only have access to the features provided by the platform, without access to the AWS console, infrastructure, and services. Barth adds:
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. You can use the Amazon Bedrock API to access those resources in downstream applications.
Source: AWS blog
Amazon Bedrock Studio supports features such as Agents, multiple Foundation Models (FMs), and various tools. Knowledge Bases implement retrieval-augmented generation (RAG), providing responses that include citations, allowing users to verify source text and ensure factual accuracy. Guardrails enable developers to implement safeguards in generative AI applications based on specific use cases and AI policies.
In the article "A first look at the brand new Amazon Bedrock Studio", Monica Colangelo, principal cloud architect at NTT DATA, highlights some of the limitations of the preview, including the requirement that the AWS IAM Identity Center must be configured in the same region where Bedrock Studio is currently available. She writes:
While the capabilities within Amazon Bedrock Studio aren't entirely new, having been previously available through the Amazon Bedrock offering, the true value proposition lies in the seamless playground environment that allows users to experiment with all these features together. This unified approach significantly lowers the barrier to entry.
There are no additional costs associated with Bedrock Studio; customers only pay for Bedrock usage. Corey Quinn, chief cloud economist at The Duckbill Group, comments:
I wonder if Bedrock Canvas is going to be next. That's what SageMaker did; those thieves still owe me $260 in credits for their predatory pricing model.
Jeremy Daly, CEO and founder of Ampt, writes instead:
Some of this stuff is getting scary good.
Banjo Obayomi, senior developer advocate at AWS, created a demo video to demonstrate how the new workspace works. Bedrock Studio is currently available in public preview in only two US regions: Northern Virginia and Oregon.