Amazon announces customer service chatbot trial

Amazon is testing out two neural network-based automated customer service systems. One can handle common customer service requests automatically and the other helps agents respond to people more easily.

Most text-based online systems feature automated agents that can handle simple requests, the e-commerce giant observes in a blog post. Typically, these agents are governed by rules, rather like flow charts that specify responses to particular customer inputs. If the automated agent can’t handle a request, it refers the request to a human customer service representative.

Amazon claims that its automated agents can handle a broader range of interactions with better results, “allowing our customer service representatives to focus on tasks that depend more on human judgement”.

In trials, its has been comparing these to its existing rule-based systems, using a metric called automation rate. This combines two factors: whether the automated agent successfully completes a transaction (without referring it to a customer service representative) and whether the customer contacts customer service a second time within 24 hours. According to that metric, the new agents significantly outperform the old ones.

Sign up for our free retail technology newsletter here.