Updated feature: Added new service tiers priority and flex for on demand inference

Amazon Bedrock Release Notes

Amazon Bedrock is a fully managed service that offers high-performing foundation models from leading AI companies and Amazon. It provides a unified API for easy experimentation, customization, and deployment of generative AI applications with security, privacy, and responsible AI.

What can I do with Amazon Bedrock?

• Experiment with prompts and configurations – Submit prompts and generate responses using different configurations and foundation models.
• Augment response generation – Create knowledge bases by uploading data sources to enhance model responses.
• Build agents – Create agents that use foundation models to reason through and carry out tasks for customers.
• Customize models – Fine-tune or continue pre-training models with your data to improve performance on specific tasks or domains.
• Purchase Provisioned Throughput – Improve efficiency and reduce costs by purchasing throughput for foundation models.
• Evaluate models – Determine the best model for your use case by evaluating outputs with built-in or custom prompt datasets.
• Use guardrails – Implement safeguards for your generative AI applications to prevent inappropriate or unwanted content.
• Optimize latency – Get faster response times with latency-optimized inference for foundation models.

What to do

• Familiarize yourself with the terms and concepts used in Amazon Bedrock.
• Understand how AWS charges for using Amazon Bedrock.
• Try the Get started with Amazon Bedrock tutorials to learn how to use the console and AWS SDK.
• Read the documentation for the features you want to include in your application.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.