Amazon Carry Out Trials On Artificial Intelligence Driven Buyer Support Agents

With the intention to find out whether Artificial Intelligence can help improve buyer service for the people who shop on Amazon.com, the company is checking out AI driven customer support agents.

In a blog post, the e-commerce giant divulged that it is testing two Artificial Intelligence based systems to handle inbound customer questions. One system registers request from customers automatically and without human involvement, while the second system aids human agents answer more rapidly and effortlessly.

In the aforementioned blog post, Jared Kramer, an applied-science manager in Amazon’s customer service technical management team, elucidated that automated representatives use ML and AI as opposed to rules and refer requirements they can’t manage to human representatives. This essentially empowers them to confront a comprehensive variety of dialogues. Notably, the new approach is conflicting to Amazon’s longstanding flow chart system that detailed replies to specific inputs.

Kramer mentioned,

“It is difficult to determine what types of conversational models other customer service systems are running, but we are unaware of any announced deployments of end-to-end, neural-network-based dialogue models like ours. And we are working continually to expand the breadth and complexity of the conversations our models can engage in, to make customer service queries as efficient as possible for our customers.”