This audio is automatically generated. Please let us know if you have any comments.
Diving brief:
- Amazon Connect announced 29 new agentic AI features on Sunday, including fully autonomous AI agents and support for human representatives, at Amazon Web Service’s re:Invent conference.
- Autonomous AI agents are capable of handling tasks across multiple channels, including voice and chat, according to AWS. They can understand complex requests with multiple intentions and take autonomous action on behalf of customers.
- New agent features include analyzing conversations, suggesting next steps for live agents, and managing tasks like documentation, according to AWS. Support agents can analyze the context of the conversation, anticipate needs, and proactively offer relevant information.
Dive overview:
The ability to communicate seamlessly between AI agents and human representatives is a critical part of Amazon Connect’s offering, according to Pasquale DeMaio, vice president of Amazon Connect.
The transfer from AI to human can be initiated at the request of a client or by the AI agent itself if it does not have the capabilities or permission to process a request, according to DeMaio. From there, the AI agent can offer context to what has already happened and help guide the call to completion.
“Agent agents don’t stop working,” DeMaio told CX Dive. “It helps the human agent understand what to do. It provides them with workflows. It provides them with answers. It can even suggest other things to do.”
For example, a customer can call a company to change the address on file, according to DeMaio. Agentic AI can understand the request, ask the necessary questions, and manage the task. However, if the customer is uncomfortable or an issue arises that requires human attention, the call can be seamlessly transferred to a live agent.
According to AWS, businesses can monitor Amazon Connect AI agents in the same way they would a human employee. Supervisors can evaluate AI interactions for accuracy, compliance, and customer satisfaction to ensure consistent quality standards.
“We’re going to give you the tools to see what the results look like and review the results of the day,” DiMaio said. Contact centers can examine customer behaviors, from individual interactions to long-term data, to help them refine agentic AI behavior.
