"Ask Me Anything": How Comcast Uses LLMs to Assist Agents in Real Time

TL;DR

This paper presents 'Ask Me Anything' (AMA), an LLM-powered tool that assists customer service agents in real-time, reducing conversation handling time and improving agent efficiency and satisfaction.

Contribution

Introduces AMA, a novel real-time LLM-based assistant for customer service agents, enhancing efficiency and user experience in enterprise settings.

Findings

Agents using AMA spent 10% less time per conversation.

Nearly 80% of agents found AMA useful.

Potential for millions of dollars in annual savings.

Abstract

Customer service is how companies interface with their customers. It can contribute heavily towards the overall customer satisfaction. However, high-quality service can become expensive, creating an incentive to make it as cost efficient as possible and prompting most companies to utilize AI-powered assistants, or "chat bots". On the other hand, human-to-human interaction is still desired by customers, especially when it comes to complex scenarios such as disputes and sensitive topics like bill payment. This raises the bar for customer service agents. They need to accurately understand the customer's question or concern, identify a solution that is acceptable yet feasible (and within the company's policy), all while handling multiple conversations at once. In this work, we introduce "Ask Me Anything" (AMA) as an add-on feature to an agent-facing customer service interface. AMA allows agents to ask questions to a large language model (LLM) on demand, as they are handling customer conversations -- the LLM provides accurate responses in real-time, reducing the amount of context switching the agent needs. In our internal experiments, we find that agents using AMA versus a traditional search experience spend approximately 10% fewer seconds per conversation containing a search, translating to millions of dollars of savings annually. Agents that used the AMA feature provided positive feedback nearly 80% of the time, demonstrating its usefulness as an AI-assisted feature for customer care.