Building a Chatbot for a Large Company: 3 Reasons Why These Projects Fail and 5 Steps How To Fix It

Abstract: Chatbots were on top of the hype in 2016 and many large companies started their Proof-of-Concept projects with the idea to augment human labor, reduce contact center expenses, and improve customer experience. Hundreds of startups are building their chatbot tools and platforms. They promise "Chatbots made easy", "Build your chatbot in 5 minutes, "Fast and easy way to build bots", etc.

But the reality is different. Conversational user experiences are not easy, and many chatbot projects fail. In this workshop, we will build a simple chatbot and discuss why chatbot implementations fail in large companies. We will review popular platforms like IBM Watson, Google API.AI, MS LUIS, and discuss the bottlenecks in the chatbot implementation process. We will identify steps and methods that help design the right conversational system for a large company.

Bio: Artemy is a CEO of Data Monsters, a Palo Alto based research lab and consulting company. Prior to Data Monsters Artemy founded a business intelligence startup, which raised $6M of venture capital and two years later was sold to a nationwide system integrator. Artemy is an expert in computational social science, knowledge mining, chaos theory.