How LY Corporation Uses Agentforce to Resolve 80% of Customer Cases

LY Corporation sits at the center of everyday digital life in Japan, operating the LINE messaging platform alongside Yahoo! JAPAN search and commerce services. With over 107 million active users and more than 100 discrete products, the company fields millions of customer inquiries each month across an enormous range of topics — from payment disputes to account issues to product-specific FAQs. Scaling high-quality support to that volume, without proportionally expanding headcount, became one of the organization’s defining operational challenges.

Before deploying Agentforce, support teams across LY’s various services operated in silos. Each service had its own channels, data systems, and workflows, making it difficult for agents to get a unified view of a customer’s history. Routine questions consumed a disproportionate share of agent time, leaving little bandwidth for complex or sensitive interactions. Email queues in particular grew long, with reply times stretching in ways that frustrated users accustomed to the instant-response experience the LINE platform itself provides.

LY Corporation built its new support architecture on Salesforce’s Agentic Enterprise stack. Agentforce agents were deployed on the Yahoo! JAPAN portal to field chat-based customer FAQs, with each response grounded in trusted knowledge bases, order data, and case history retrieved in real time. MuleSoft was used to integrate the enterprise context — pulling data from the 100-plus services into unified customer profiles that both AI agents and human reps can access. For internal collaboration, all 27,000 employees across the group’s companies were connected on Slack, enabling teams to coordinate around AI-assisted workflows and share context across organizational boundaries.

The standout result is that Agentforce now resolves 80% of incoming customer support cases without any human involvement. On the email channel alone, the platform handles 48,000 routine inquiries per month — filtering out 99.9% of spam, resolving common questions instantly, and routing complex cases to human agents with full context attached. For the Yahoo! JAPAN portal, the system handles 25,000 FAQ interactions each month through agentic chat.

For LY Corporation, the shift signals more than efficiency gains. It demonstrates that a company operating at internet scale can unify fragmented support systems under a single intelligent layer without sacrificing service quality. Executive Officer and CIO Norihiro Hattori has framed this as a model for how LY will scale personalized experiences as the user base grows — with agentic infrastructure handling volume while human agents focus on relationships that require judgment and empathy.