E-Commerce customer support requires quick and accurate answers grounded in product data and past support cases. This paper develops a novel retrieval-augmented generation (RAG) framework that uses knowledge graphs (KGs) to improve the relevance of the answer and the factual grounding. We examine recent advances in knowledge-augmented RAG and chatbots based on large language models (LLM) in customer support, including Microsoft's GraphRAG and hybrid retrieval architectures. We then propose a new answer synthesis algorithm that combines structured subgraphs from a domain-specific KG with text documents retrieved from support archives, producing more coherent and grounded responses. We detail the architecture and knowledge flow of our system, provide comprehensive experimental evaluation, and justify its design in real-time support settings. Our implementation demonstrates 23\% improvement in factual accuracy and 89\% user satisfaction in e-Commerce QA scenarios.

Airbnb is an online marketplace that connects hosts and guests to unique stays and experiences. When guests stay at homes booked on Airbnb, there are a small fraction of stays that lead to support needed from Airbnb's Customer Support (CS), which may cause inconvenience to guests and hosts and require Airbnb resources to resolve. In this work, we show that instances where CS support is needed may be predicted based on hosts and guests behavior. We build a model to predict the likelihood of CS support needs for each match of guest and host. The model score is incorporated into Airbnb's search ranking algorithm as one of the many factors. The change promotes more reliable matches in search results and significantly reduces bookings that require CS support.

Teleperformance, the largest call-center operator in the world, is rolling out an artificial intelligence system that softens English-speaking Indian workers' accents in real time in a move the company claims will make them more understandable. The technology, called accent translation, coupled with background noise cancellation, is being deployed in call centers in India, where workers provide customer support to some of Teleperformance's international clients. Teleperformance provides outsourced customer support and content moderation to global companies including Apple, ByteDance's TikTok and Samsung Electronics. "When you have an Indian agent on the line, sometimes it's hard to hear, to understand," Deputy-CEO Thomas Mackenbrock said in an interview with Bloomberg. The technology can "neutralize the accent of the Indian speaker with zero latency," he said.

The growing reliance on artificial intelligence (AI) in customer support has significantly improved operational efficiency and user experience. However, traditional machine learning (ML) approaches, which require extensive local training on sensitive datasets, pose substantial privacy risks and compliance challenges with regulations like the General Data Protection Regulation (GDPR) and California Consumer Privacy Act (CCPA). Existing privacy-preserving techniques, such as anonymization, differential privacy, and federated learning, address some concerns but face limitations in utility, scalability, and complexity. This paper introduces the Privacy-Preserving Zero-Shot Learning (PP-ZSL) framework, a novel approach leveraging large language models (LLMs) in a zero-shot learning mode. Unlike conventional ML methods, PP-ZSL eliminates the need for local training on sensitive data by utilizing pre-trained LLMs to generate responses directly. The framework incorporates real-time data anonymization to redact or mask sensitive information, retrieval-augmented generation (RAG) for domain-specific query resolution, and robust post-processing to ensure compliance with regulatory standards. This combination reduces privacy risks, simplifies compliance, and enhances scalability and operational efficiency. Empirical analysis demonstrates that the PP-ZSL framework provides accurate, privacy-compliant responses while significantly lowering the costs and complexities of deploying AI-driven customer support systems. The study highlights potential applications across industries, including financial services, healthcare, e-commerce, legal support, telecommunications, and government services. By addressing the dual challenges of privacy and performance, this framework establishes a foundation for secure, efficient, and regulatory-compliant AI applications in customer interactions.

Tool-augmented LLMs are a promising approach to create AI agents that can have realistic conversations, follow procedures, and call appropriate functions. However, evaluating them is challenging due to the diversity of possible conversations, and existing datasets focus only on single interactions and function-calling. We present a test generation pipeline to evaluate LLMs as conversational AI agents. Our framework uses LLMs to generate diverse tests grounded on user-defined procedures. For that, we use intermediate graphs to limit the LLM test generator's tendency to hallucinate content that is not grounded on input procedures, and enforces high coverage of the possible conversations. Additionally, we put forward ALMITA, a manually curated dataset for evaluating AI agents in customer support, and use it to evaluate existing LLMs. Our results show that while tool-augmented LLMs perform well in single interactions, they often struggle to handle complete conversations. While our focus is on customer support, our method is general and capable of AI agents for different domains.

One of today's primary priorities of companies is to improve the Customer Experience (CX) to increase customer satisfaction and reduce churn. However, "just 2 percent of organizations reached the top stage of CX maturity [and] most organizations are in early stages of CX maturity" (Dorsey et al., 2022). According to a recent study by Qualtrics (2022), 47 percent of customers ranked support as the second most important area of improvement in CX. One major factor of customer satisfaction identified in recent research (e.g., Service Excellence Research Group, 2021) is the speed at which customer support answers customer inquiries. Demand for customer support is rising and often exceeds the supply of available support agents. Especially missing knowledge and multiple re-routings between support agents are major factors for delays in resolution time. Further research suggests that due to information overload, the quality of decisions decreases with the number of decisions (Hemp, 2009; Viegas et al., 2015). In most recent studies, lack of time and resources are mentioned as the main issues in customer support, which harm the performance and, ultimately, the customer experience (HubSpot, 2022; Serrano et al., 2021).

Recently Jon Stewart did a segment poking satire at the promises of AI highlighted by tech CEOs. I don't think automating your toasters is the best way to show the potential of AI, as Jon did, but I do agree with the central premise of his argument that disruption caused by AI will be harnessed to prioritize profits over people. It will likely cause one of the largest and fastest labor displacements in human history. I run an AI company based in Silicon Valley focused on solving climate change, and I am a former policymaker for the government of India. At the World Economic Forum Davos 2024, my discussions with media, heads of state, and CEOs of Fortune 500 companies underscored global perspectives on AI, where AI was widely discussed to unlock the next productivity revolution, foster wealth creation, and uplift people out of poverty by democratizing and reducing the cost of access to information/education.

Accurately predicting the intent of customer support requests is vital for efficient support systems, enabling agents to quickly understand messages and prioritize responses accordingly. While different approaches exist for intent detection, maintaining separate client-specific or industry-specific models can be costly and impractical as the client base expands. This work proposes a system to scale intent predictions to various clients effectively, by combining a single generic model with a per-client list of relevant intents. Our approach minimizes training and maintenance costs while providing a personalized experience for clients, allowing for seamless adaptation to changes in their relevant intents. Furthermore, we propose a strategy for using the clients relevant intents as model features that proves to be resilient to changes in the relevant intents of clients -- a common occurrence in production environments. The final system exhibits significantly superior performance compared to industry-specific models, showcasing its flexibility and ability to cater to diverse client needs.

Businesses have sought out new solutions to provide support and improve customer satisfaction as more products and services have become interconnected digitally. There is an inherent need for businesses to provide or outsource fast, efficient and knowledgeable support to remain competitive. Support solutions are also advancing with technologies, including use of social media, Artificial Intelligence (AI), Machine Learning (ML) and remote device connectivity to better support customers. Customer support operators are trained to utilise these technologies to provide better customer outreach and support for clients in remote areas. Interconnectivity of products and support systems provide businesses with potential international clients to expand their product market and business scale. This paper reports the possible AI applications in customer support, done in collaboration with the Knowledge Transfer Partnership (KTP) program between Birmingham City University and a company that handles customer service systems for businesses outsourcing customer support across a wide variety of business sectors. This study explored several approaches to accurately predict customers' intent using both labelled and unlabelled textual data. While some approaches showed promise in specific datasets, the search for a single, universally applicable approach continues. The development of separate pipelines for intent detection and discovery has led to improved accuracy rates in detecting known intents, while further work is required to improve the accuracy of intent discovery for unknown intents.

Boris Kontsevoi is a technology executive, President and CEO of Intetics Inc., a global software engineering and data processing company. AI used to be the stuff of sci-fi movies, but now it's all around us--computer vision and chatbots have become part of the standard business processes. Recently, artificial intelligence has reached its peak and made a breakthrough that has affected almost every industry, from high tech, telecoms, finance and healthcare to pharmaceuticals. The global AI market is expected to grow by more than $500 billion between now and 2030, according to various studies. IDC, a market research firm, predicted that the AI market will be worth over $500 billion by 2024.