Overview

Amazon Bedrock IDE (preview), a governed collaborative environment integrated within Amazon SageMaker Unified Studio (preview), enables developers to swiftly build and tailor generative AI applications. It provides an intuitive interface with access to Amazon Bedrock's high-performing foundation models (FMs) and advanced customization capabilities like Knowledge Bases, Guardrails, Agents, and Flows. This secure environment empowers teams to accelerate the development of generative AI applications tailored to their requirements and responsible AI guidelines.

Enable effortless generative AI development across skill levels

Amazon Bedrock IDE simplifies the development of generative AI applications by providing an effortless and accessible experience for developers across all skill levels. With its intuitive interface and streamlined workflows, developers can seamlessly collaborate on projects, leveraging Amazon Bedrock's powerful capabilities. They also gain governed access to data, accelerating the prototyping, iteration, and deployment of production-ready, generative AI apps aligned with business needs.

Bedrock Studio welcome screen

Build custom generative AI applications

Developers can tailor foundation models to their requirements, data, workflows, and ethical standards. They can leverage capabilities like Retrieval Augmented Generation (RAG) to create Knowledge Bases from their proprietary data sources, ensuring model responses are tailored to their specific business needs. Additionally, they can build chat agent apps using Agents, add Guardrails for safeguarding and privacy, and leverage advanced features like prompt engineering, functions, and Flows for rapid iteration – all without delving into underlying services.

Bedrock Studio healthcare chatbot screen

Collaborate seamlessly among stakeholders

Amazon Bedrock IDE, integrated within Amazon SageMaker Unified Studio, fosters seamless collaboration across various teams, including business and technical stakeholders with varying skillsets. Users can collectively build, customize, and share generative AI applications in a secure manner, enabling trusted cross-functional collaboration. This empowers teams to work together on a wide range of generative AI applications such as company-specific content generation, workflow automation, and software development.

Bedrock Studio healthcare insurance screen

Evaluate and adopt high-performing models with ease

Amazon Bedrock IDE provides access to a wide range of high-performing FMs from leading AI companies. The generative AI playground experience simplifies model evaluation by allowing developers to compare different models and configurations. Automated model evaluation further helps users assess performance, quality, and safety metrics, enabling them to easily identify and adopt the model suited for their specific use case.

Bedrock Studio workspace screen

Implement responsible AI guardrails

Developers can create guardrails and set content filters on both user input and model responses to help make their generative AI app generate appropriate outputs. They can customize guardrail behavior by setting filtering levels across various categories and adding denied topics, aligning their applications with responsible AI guidelines and desired outputs.

Bedrock Studio guardrails screen

Customers

  • Adastra

    We build complex data analytics, ML and GenAI applications with built-in data governance and user-friendly interfaces. Before Amazon SageMaker Unified Studio, deploying multiple tools for our customers' data and information workers was mostly manual and time-consuming, and ensuring a robust data architecture provisioning was a challenge. Now, with Amazon SageMaker Unified Studio, we can deploy a single data worker tool for data engineers and ML scientists. We will also be able to automate data infrastructure deployment, allowing us to simplify the process for our customers and enhance their experience.

    Zeeshan Saeed, Chief Technology and Strategy Officer, Adastra

  • Toyota

    To address siloed data sets spread across our automotive operations, we are exploring Amazon SageMaker to unify and govern data across our connected car, sales, manufacturing, and supply chain units. This approach allows us to search, discover, and share data effortlessly, laying the groundwork for pre-empt quality issues, increase customer safety and satisfaction, and easier development of generative AI applications.

    Kamal Distell, VP of Data, Analytics, Platforms, and Data Science, TMNA