AWS Adds Generative AI to Amazon Connect

Amazon Web Services today at its At AWS re:Invent user conference in Las Vegas introduced generative artificial intelligence capabilities it's added in Amazon Connect, its cloud contact center.

Powered by large language models (LLMs) and other foundation models (FMs) available through Amazon Bedrock, the latest Amazon Connect enhancements include generative AI capabilities that expand on machine learning (ML) features already present in the solution.

The new generative AI capabilities of Amazon Connect include the following:

  • Amazon Q in Connect, to assist agents with recommended responses and actions, helps understand customer intents and uses relevant sources of information to deliver accurate responses and actions in real time.
  • Amazon Connect Contact Lens, for post-contact summarization. Moments after a customer interaction, Amazon Connect Contact Lens identifies important details of the customer conversation, such as the customer's issue, the actions taken by the agent, and the next steps required to close the loop with the customer, and generates a short summary.
  • Amazon Lex in Amazon Connect, to simplify bot or interactive voice response (IVR) building by describing in natural language what they want the self-service system to accomplish. Using this prompt, Amazon Lex will generate sample utterances and create a chatbot or IVR. When customers reply to chatbots or IVRs with less common responses, Amazon Connect leverages models to correctly interpret the customer's response. Contact center administrators can also create question-and-answer chatbots and IVRs directly using Amazon Lex, which will generate responses for common customer questions by searching through an organization's knowledge base and summarizing the most relevant details.
  • Amazon Connect Customer Profiles, for the automatic creation of unified customer profiles for personalized customer experiences. When contact center administrators add data sources, such as Adobe Analytics, Salesforce, ServiceNow, Zendesk or Amazon Simple Storage Service (S3), Amazon Connect Customer Profiles will analyze the data to understand what the data format and content represent and how the data relates to customers' profiles. Amazon Connect Customer Profiles then determines how to organize and combine data from different sources into complete, accurate profiles. Managers can review, make edits, and complete the setup of customer profiles.

"The contact center industry is poised to be fundamentally transformed by generative AI, offering customer service agents, contact center supervisors, and contact center administrators new ways to deliver personalized customer experiences even more effectively. Yet few organizations have the advanced machine learning expertise to easily harness this technology and apply it to their operations," said Pasquale DeMaio, vice president of Amazon Connect at AWS Applications, in a statement. "With just a few clicks, contact center leaders can leverage new capabilities powered by generative AI in Amazon Connect to enhance the more than 15 million customer interactions handled on Amazon Connect every day. With these new capabilities, contact centers can consistently deliver improved customer support at scale."

In addition to these new generative AI enhancements, Amazon Connect has extended omnichannel capabilities to include out-of-the-box support for two-way SMS messaging, as well as in-app and web voice calling with support for video.