Use Case Intelligence RSS Search use cases Search
MongoDB Telecommunications South Korea

LG U+

Customer Service Automation

LG U+ needed a scalable document-oriented foundation for its Agent Assist call-center system because relational databases could not efficiently manage the complex and unstructured data behind real-time support workflows.

Read the original story Explore all use cases
Agent Assist improved resource efficiency by 30 percent.
LG U+ operates one of the largest customer service centers in Korea, with 4,000 agents handling 3.5 million calls per month.
“The service has enhanced efficiency by reducing processing time by 7 percent on average per call.”

Reported impact

Business outcome

LG U+ improved resource efficiency by 30%, reduced average processing time per call by 7%, and launched a high-volume AI support service that performs reliably even during peak periods.

  • Customer Experience
  • Productivity Improvement
  • Scalability

Solution

LG U+ built its Agent Assist contact-center solution on MongoDB Atlas and Atlas Vector Search to help thousands of service agents access the right information faster during live calls. The platform combines operational customer-service data with vectorized knowledge so the AI system can transcribe conversations, categorize intent, summarize context, and recommend answer guidelines in real time. By moving operational data off PostgreSQL and into Atlas, LG U+ eliminated redundant processes and gained a single environment for document and vector data. Atlas Vector Search gives the AI layer fast semantic retrieval, while the Atlas document model lets the engineering team adapt data structures quickly as the service evolves. The implementation moved from development to launch in four months, giving the call center a more responsive backend for high volumes while reducing delays that previously hurt agent productivity and customer experience.

Data flow

Customer-service interactions and operational records are stored in MongoDB Atlas, indexed with Atlas Vector Search for semantic retrieval, and then used by Agent Assist to transcribe calls, categorize intent, summarize context, and recommend answers back to live agents.

Solution architecture

2 components · 2 layers
  1. Storage
    • MongoDB Atlas Stores operational contact-center data and supports the fast document model Agent Assist depends on.
  2. Serving
    • Atlas Vector Search Retrieves semantically relevant information in real time so Agent Assist can guide customer-service agents during live calls.

Architecture clues

  • LG U+ launched Agent Assist within four months of implementing MongoDB Atlas.
  • MongoDB consolidates vector and operational data in a single system.
  • The platform identifies customer intent and suggests answer guidelines in real time.
  • The prior operational data environment was based on PostgreSQL.

Evidence from the source

“Agent Assist addresses these challenges with real-time transcription, automatic categorization of customer inquiries, and intelligent contextual summaries.”
“Managing both vector and operational data in MongoDB opened a new world to our team.”
“The service has enhanced efficiency by reducing processing time by 7 percent on average per call.”
“Using MongoDB’s flexible document model to manage both vector and operational data has improved resource efficiency by 30 percent.”
Transparency Evidence & methodology 100/100 reference value · 89% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    2 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    4 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. MongoDB

    LG U+ customer story

    First-party
    https://www.mongodb.com/solutions/customer-case-studies/lgu
    Source type
    Vendor-published customer story
    Published
    Oct 31, 2025
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Oct 31, 2025 · MongoDB · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Cognizant Archived · Oct 9, 2026 Cox Communications Telecommunications North America Cox Communications needed to modernize a high-volume chatbot and IVR estate so customers could get accurate, relevant answers across preferred channels without overloading live support teams. 17% improvement in first-contact resolution for chatbot Customer Service Automation Gemini Enterprise for Customer Experience (CX) · Google Cloud Contact Center as a Service (CCaaS) · Google Dialogflow CX Google Cloud Archived · Sep 9, 2026 AT&T Telecommunications United States AT&T needed to route customers more accurately, increase autonomous issue containment, and make virtual assistants feel more personal instead of forcing users through repetitive phone trees and stateless support… 20% more calls autonomously Customer Service Automation BigQuery · Gemini Enterprise for Customer Experience Google Cloud Archived · Aug 29, 2026 Bell Canada Telecommunications Canada Bell needed to move beyond rigid support decision trees and fragmented agent tooling so it could resolve more customer inquiries autonomously while still personalizing interactions across chat, voice, and human-assisted… Handled 16M+ chat interactions, with over half resolved by AI Customer Service Automation Agent Assist · BigQuery · Gemini for customer experience