On the care and feeding of virtual assistants: Automating conversation review with AI

Abstract

With the rise of intelligent virtual assistants (IVAs), there is a necessary rise in human effort to identify conversations containing misunderstood user inputs. These conversations uncover error in natural language understanding and help prioritize improvements to the IVA. As human analysis is time consuming and expensive, prioritizing the conversations where misunderstanding has likely occurred reduces costs and speeds IVA improvement. In addition, less conversations reviewed by humans mean less user data are exposed, increasing privacy. We describe Trace AI, a scalable system for automated conversation review based on the detection of conversational features that can identify potential mis-communications. Trace AI provides IVA designers with suggested actions to correct understanding errors, prioritizes areas of language model repair, and can automate the review of conversations. We discuss the system design and report its performance at identifying errors in IVA understanding compared to that of human reviewers. Trace AI has been commercially deployed for over 4 years and is responsible for significant savings in human annotation costs as well as accelerating the refinement cycle of deployed enterprise IVAs.