Amazon Lex is a service for building conversational interfaces into any application using voice and text. With Amazon Lex, you can quickly and easily build sophisticated, natural language, conversational bots (“chatbots”), virtual agents, and IVR systems. Today, Amazon Lex introduces multi-valued slots. A slot is used to capture user responses as the bot gathers information to fulfill a user request. In some cases, the information can be a list of multiple values. For example, when conversing with an insurance bot, a customer may request quotes for insurance premiums. When the bot requests them to specify which insurance type, the customer may respond with more than one type and say “I need quotes for home, auto, and boat premiums.” With multi-value slots, Amazon Lex can now capture the customer’s response in a single response with no special coding required.

We are excited to announce that Amazon Personalize now enables customers to unlock the information trapped in their product descriptions, reviews, movie synopses or other unstructured text to generate highly relevant recommendations for users. Product descriptions contain important information and insights about products. The investments made to create these narratives enable the creation of more relevant user recommendations for products, movies, TV shows, news articles and more. Customers provide unstructured text as part of their catalog and, using state-of-the-art natural language processing (NLP) techniques, Amazon Personalize automatically extracts key information about the items in your catalog to use when generating recommendations for your users.

Today, AWS Copilot announced the release of version 1.8. With this release, AWS Copilot now allows you to configure a friendly DNS name for your load balanced web services deployed with Amazon Elastic Container Service (Amazon ECS) Customers can now provide a friendly DNS name, such as api.example.com, directly in the manifest file and Copilot will provision and manage the necessary infrastructure to associate the domain name with the application load balancer.

AWS Key Management Service (AWS KMS) is introducing multi-Region keys, a new capability that lets you replicate keys from one AWS Region into another. With multi-Region keys, you can more easily move encrypted data between Regions without having to decrypt and re-encrypt with different keys in each Region. Multi-Region keys are supported for client-side encryption in the AWS Encryption SDK, AWS S3 Encryption Client, and AWS DynamoDB Encryption Client. They simplify any process that copies protected data into multiple Regions, such as disaster recovery/backup, DynamoDB global tables, or for digital signature applications that require the same signing key in multiple Regions.

AWS Amplify CLI now supports IAM permission boundaries to limit Amplify-generated IAM roles. The AWS Amplify CLI is a command line toolchain that helps frontend developers create app backends in the cloud that include IAM roles controlling access to AWS resources. With IAM permissions boundaries, Amplify-generated IAM roles can perform only the actions that are allowed by both the roles’ policies and permissions boundary.

Amazon MQ is now available in a total of 24 regions, with the addition of both AWS GovCloud (US) Regions. AWS GovCloud (US) Regions are isolated AWS Regions designed to host sensitive data and regulated workloads in the cloud, assisting customers who have United States federal, state, or local government compliance requirements.

Starting today, AWS customers can use Amazon Kendra to build intelligent search applications in the Canada (Central) and US East (Ohio) AWS Regions.

AWS Gateway Load Balancer is now available in both AWS GovCloud (US) Regions. The expansion into the AWS GovCloud (US) Regions enables U.S. government agencies and contractors to move more sensitive workloads into the cloud by helping them to address certain regulatory and compliance requirements. With this launch, AWS Gateway Load Balancer is now available in 25 regions.

AWS EC2 F1 instances have been used by customers to accelerate a growing set of applications from genomic processing, data analytics, security, image/video analytics, machine learning and more. Developers have taken advantage of the FPGA developer kit  and current standard F1.X.1.4 shells to easily build and deploy their applications.

Workflow Studio is a new visual workflow designer for AWS Step Functions that makes it faster and easier to build workflows using a drag and drop interface in the AWS console.