Using Sendbird on AWS, the South Korean e-commerce giant automated first-tier customer service, reducing human agent workload by 40% without compromising quality.
21 de novembro de 2025
7 min read
Source: aws.amazon.com
-40%
Human Workload
AI
Intelligent Routing
AWS
Cloud Infrastructure
Lotte Homeshopping, one of South Korea's largest e-commerce companies, implemented a conversational AI solution using Sendbird on AWS infrastructure to automate first-tier customer service. The result was a 40% reduction in human agent workload, allowing the team to focus on complex cases requiring personalized attention.
This case demonstrates how the combination of conversational AI with intelligent routing can transform customer service operations at scale, maintaining quality while significantly reducing operational costs.
-40%
Human Workload
AI
Intelligent Routing
AWS
Cloud Infrastructure
With millions of customers and a diverse product catalog, Lotte Homeshopping faced an ever-growing volume of customer inquiries — from order tracking and return processing to product questions and complaints.
The majority of interactions were repetitive and followed predictable patterns ("where is my order?", "how do I return?", "is this product available?"), but each one consumed time from human agents who could have been dedicated to more complex and high-value cases.
The implemented solution combines several layers of automation:
Intelligent Triage: AI classifies each incoming request by type, urgency, and complexity
Automated Resolution: Frequently asked questions and simple processes (order tracking, return status) are resolved entirely by AI
Smart Routing: Complex cases are directed to the most qualified agent based on specialization and availability
Agent Assistance: Even for human-handled cases, AI provides relevant context and recommended responses
The Sendbird infrastructure on AWS ensures scalability to handle demand spikes (such as promotions and holidays) without performance degradation.
Implementation was gradual, starting with the simplest categories and expanding as the model was validated and refined.
The main result was a 40% reduction in the workload on human agents, which translated into:
- More time for agents to dedicate to complex and high-value cases - Improvement in CSAT for complex cases (agents less pressured and more focused) - Reduction in average wait time for all customers - Operational cost savings without team reduction (reallocation to strategic functions) - Scalable infrastructure that handles demand spikes without bottlenecks
Catalisa enables the implementation of intelligent triage and automated resolution solutions with AI Agents that understand the context of each request and automatically decide the best resolution path.
With Catalisa's Building Blocks, integration with order management systems, CRMs, and e-commerce platforms is simplified, allowing AI to access real-time data for accurate and personalized responses.
Catalisa's Workflows orchestrate the complete support flow — from initial classification to resolution or escalation — with monitoring and continuous improvement metrics.
AWS BLOG. “Lotte Homeshopping reduces human agent workload by 40% with Sendbird on AWS”. aws.amazon.com. Disponível em: https://aws.amazon.com/pt/blogs/industries/lotte-homeshopping-reduces-human-agent-workload-by-40-with-sendbird-on-aws/. Acesso em: 27 fev. 2026.
Schedule a demo and see how Catalisa can transform your business
Analysis of how companies like Boticário, Carrefour, Magazine Luiza, and Lotte are using conversational AI to reshape the relationship between brands and consumers.
11 de fev. de 2026
·
10 min read
How Synthesia, Lotte, and Carrefour absorbed exponential growth in service demands without proportional hires, using AI as a force multiplier.
04 de fev. de 2026
·
9 min read
Quantitative analysis of the real return on AI investment in customer experience, with consolidated data from Forrester, Boticário, Lotte, and Synthesia.
27 de dez. de 2025
·
10 min read
© 2026 Catalisa. Todos os direitos reservados.
Conforme LGPD
Meta WhatsApp Business
Dados no Brasil
We use cookies for analytics and load external resources (images) to improve your experience. By clicking "Accept", you consent to the use of cookies and third-party resources in accordance with our Privacy Policy.