Amazon Lex brings automated call transcript review to chatbot building

Today, at AWS re:Invent in Las Vegas, the company announced the Amazon Lex automated chat bot designer in preview, a new feature that simplifies the chatbot training and design process by bringing a level of automation to it.

“We are excited to announce the Amazon Lex automated chat bot designer, a new capability that reduces bot design from weeks to just hours,” Swami Sivasubramanian, VP of Amazon AI told the audience at the AI and machine learning keynote today.

It does this by taking advantage of advanced natural language understanding powered by deep learning techniques. In fact, he said that developers can now create a foundational chatbot designed using historical call transcripts in just a few clicks.

“[The Amazon Lex] automated chat bot designer can typically analyze 10,000 lines of transcripts within a couple of hours to identify intents such as ‘file a new claim’ or ‘check claim status.’ It makes sure these intents are well separated and there is no overlap between them, eliminating the need for a trial and error approach,” he explained.

He said that without this automation, it’s a highly manual and tedious developer task. “The organizational design of a chatbot is highly complex, manual and prone to errors. It requires understanding the nuances of a spoken language and human interactions, and without this specific expertise, developers spend hundreds of hours combing through all the historic called transcripts to find things like common user requests and the required information to to solve this problem.”

When you think about a common use case for AI, chatbots certainly come to mind. They may be designed for in-house use to answer questions about how to order a new computer or get your newborn child on the company health insurance, or they may act as a customer service front end to collect vital information and answer simple questions, while funneling more complex questions to a human customer service agent.

Many startups have launched to make it easier to create more accurate chatbots, but it’s also low-hanging fruit for a company like Amazon, whose customers may be looking for a solution on the platform to go with their other AI and machine learning projects.

The Amazon Lex automated chat builder is available starting today in preview. Developers can use this feature for free during the preview phase, but will be charged based on the time it takes the tool to analyze a transcript and identify the intents once it is generally available.