TechnologyCustomer Service

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

LY Corporation operates Japan’s largest digital ecosystem, running messaging app LINE and internet portal Yahoo! JAPAN for over 107 million users across more than 100 services. The company deployed Salesforce Agentforce to handle customer support at scale, with AI agents resolving routine inquiries via chat and email. The result: 80% of cases now close without human involvement, and 48,000 email inquiries are resolved automatically each month.

Impact

80%

Customer cases resolved by Agentforce

48,000

Email inquiries resolved per month

25,000

FAQ interactions handled per month

27,000

Employees connected on Slack

99.9%

Spam filtered from email queue

Challenge

LY Corporation’s more than 100 services each operated independent support systems and data stores, making it impossible to give agents a unified customer view or efficiently route the millions of routine inquiries that arrived each month.

Solution

Salesforce Agentforce was deployed to handle agentic chat and email support, grounded in real-time knowledge and order data. MuleSoft integrated enterprise context across all services into unified customer profiles, while Slack connected 27,000 employees across the group for AI-assisted collaboration.

Tools & Technologies

Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

Full Story

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.

Similar Cases

R
reMarkable
35%
support cases autonomously resolved by agentforce agent

reMarkable built two Agentforce-powered AI agents — 'Mark' for customer support and 'Saga' for internal IT help — autonomously resolving 35% of inbound support cases and significantly reducing IT team workload, enabling the company to scale without proportional headcount growth.

TechnologySSSalesforce Service CloudSDSalesforce Data Cloud
C
CANCOM
2x
adoption growth of cancom assistant

CANCOM, a leading EMEA digital solutions provider, built an AI-powered assistant using ServiceNow's Now Assist and generative AI to unify internal and customer-facing services. The CANCOM Assistant deflects 80% of support tickets across all departments and doubled adoption within a single year. The solution connects IT, HR, finance, supply chain, and sales onto one unified platform powered by agentic AI.

TechnologyNANow AssistCACANCOM Assistant
O
OpenTable
70%
diner and restaurant inquiries resolved autonomously

OpenTable deployed Salesforce Agentforce across restaurant and diner support channels, autonomously resolving 70% of inquiries and handling 73% of restaurant web queries within 3 weeks — projected to resolve 180,000 cases annually.

TechnologySSSalesforce Service CloudSDSalesforce Data Cloud
A
Allspice
20% → 97%
ingredient matching accuracy

Allspice, a food technology startup building a kitchen operating system for consumers and recipe publishers, deployed Pinecone’s vector database to solve the inherent messiness of ingredient data that traditional text search could not handle. The implementation raised ingredient matching accuracy from roughly 20% to 97%, enabling the launch of recipe importing as a core product feature and expanding into a platform-wide semantic layer for search, recommendations, and conversational AI.

TechnologyTtext-embedding-3-largePPinecone
S
Sommo
500–800
additional leads generated monthly

Sommo built an AI-powered SRS generator in Make in a single day, generating 500–800 additional leads per month and achieving a 5x increase in active website users.

TechnologyMMakeOOpenAI
C
Confluent
15,000+
hours saved monthly

Confluent, a data streaming platform company with 2,000+ employees and 4,000+ customers, deployed Glean to solve the knowledge fragmentation that came with rapid growth from 250 to 2,000+ employees across 20+ systems. Glean indexed the company's full tool stack — Slack, Salesforce, Confluence, and more — enabling instant knowledge retrieval across all teams. The result: 15,000+ hours saved monthly, a 13% increase in support team satisfaction, and over 70% employee adoption.

TechnologyGGlean
H
Headstart
90–97%
code written by claude

Headstart, an AI-native software studio, uses Claude 3.5 Sonnet to write 90-97% of client code, compressing enterprise software project timelines from months to weeks and delivering 10-100x development speed.

TechnologyC3Claude 3.5 Sonnet
M
Motive
2,000+
ai agents deployed

Motive, an AI platform for physical operations serving nearly 100,000 customers, deployed Glean across its workforce to democratize enterprise AI through unified search and agentic workflows. The company has deployed over 2,000 AI agents, cut account planning time by 75%, and reports thousands of hours saved per week across teams.

TechnologyGGleanGAGlean Agent Builder