Practice Quiz
A developer is building a generative AI application using Amazon Bedrock. The application needs to orchestrate interactions between foundation models, APIs, and data sources without requiring the developer to write custom code for prompt engineering or memory management. Additionally, the developer needs to examine the step-by-step reasoning process of the orchestration during testing. Which Amazon Bedrock capability and feature combination meets these requirements?
Amazon Bedrock Agents orchestrate interactions between foundation models, data sources, software applications, and user conversations. They automatically manage prompt engineering, memory, encryption, and API invocation without requiring provisioned capacity or custom code. To inspect the agent's reasoning process step-by-step during testing, developers use traces.
When configuring a new Amazon Bedrock Agent to perform automated tasks, what is the minimum component configuration requirement according to Amazon Bedrock design?
To configure an Amazon Bedrock Agent, the design requirement dictates that a developer must add at least an action group that the agent can perform, or associate a knowledge base to augment response performance. Other aspects like prompt engineering, memory, encryption, and capacity are managed automatically by Amazon Bedrock.
An organization needs to unify data access across its Amazon S3 data lakes and Amazon Redshift databases. At the same time, the compliance team wants to securely discover, govern, and collaborate on data and AI assets using a catalog built on Amazon DataZone. Which set of Amazon SageMaker capabilities should the organization use to achieve these goals?
According to the provided facts, the Amazon SageMaker platform incorporates SageMaker Lakehouse to unify data access across sources like S3 and Redshift, as well as SageMaker Data and AI Governance (built on Amazon DataZone) to securely discover, govern, and collaborate on data and AI. Other options, such as managed algorithms, workflows, and distributed training, are used to build, train, and deploy models rather than unify or govern data assets.
Verified References
A software development team at a startup wants to build and scale a new generative AI application to automate customer support interactions. Which AWS service is specifically designed to build and scale generative AI applications?
According to the AWS documentation, Amazon Bedrock is used to build and scale generative AI applications. Other SageMaker capabilities are designed for other tasks such as unified development environments (SageMaker Unified Studio), unifying data access (SageMaker Lakehouse), or preparing and integrating data (SageMaker Data Processing).
Verified References
A financial organization needs to securely discover, govern, and collaborate on data and AI. They want a capability that integrates with Amazon SageMaker Catalog and is built on Amazon DataZone. Which SageMaker feature should they implement?
Amazon SageMaker Data and AI Governance is built on Amazon DataZone and integrates with Amazon SageMaker Catalog to allow organizations to securely discover, govern, and collaborate on data and AI.
Verified References
Ready to test your recall?
A developer is building a generative AI application using Amazon Bedrock. The application needs to orchestrate interactions between foundation models, APIs, and data sources without requiring the developer to write custom code for prompt engineering or memory management. Additionally, the developer needs to examine the step-by-step reasoning process of the orchestration during testing. Which Amazon Bedrock capability and feature combination meets these requirements?
How confident are you in this answer?