Customer Service Operations: A Gatekeeper Framework

TL;DR

The paper addresses how to design and operate multichannel customer service systems where each channel acts as a gatekeeper with an $S$-stage resolution process, balancing throughput, cost, and quality. It develops a finite-horizon dynamic program over states $(X,Q,A)$ to characterize optimal inside-channel transfer policies and shows that, under stationarity, the policy collapses to a small set of rules; it also provides a threshold policy sufficient condition and extends the model to include queueing with a waiting room. The study then expands to AI-enabled design, analyzing multiple live agents, the chatbot channel, and customer channel-choice behavior to derive joint channel design recommendations. Numerical results illustrate that chatbot adoption can improve service quality and that hybrid human-bot architectures often yield the best performance, with optimal chatbot capability typically moderate in practice. The framework offers actionable guidance for channel selection, staffing, chatbot investment, and within-channel resolution policies, highlighting the indirect effects of AI on staffing and service policies as well as the value of structured gatekeeping in service operations.

Abstract

Customer service has evolved beyond in-person visits and phone calls to include live chat, AI chatbots and social media, among other contact options. Service providers typically refer to these contact modalities as "channels". Within each channel, customer service agents are tasked with managing and resolving a stream of inbound service requests. Each request involves milestones where the agent must decide whether to keep assisting the customer or to transfer them to a more skilled -- and often costlier -- provider. To understand how this request resolution process should be managed, we develop a model in which each channel is represented as a gatekeeper system and characterize the structure of the optimal request resolution policy. We then turn to the broader question of the firm's customer service design, which includes the strategic problem of which channels to deploy, the tactical questions of at what level to staff the live-agent channel and to what extent to train an AI chatbot, and the operational question of how to control the live-agent channel. Examining the interplay between strategic, tactical, and operational decisions through numerical methods, we show, among other insights, that service quality can be improved, rather than diminished, by chatbot implementation.

Figures (7)

• Figure 1: Typical Customer Service Desk Architecture Implemented by BlackBeltHelp
• Figure 2: Value-To-Go After Failed Attempt $X$ For Each Action And Congestion State $(Q,A)$
• Figure 3: Profit Per Period by Arrival Intensity Under Admissible Policies for Waiting Room Capacity Six
• Figure 4: Optimal Profit Per Period by Arrival Intensity with and without Waiting Room
• Figure 5: Customer Channel Choice Model