ITSOLUTION
Cases

From data systems to AI transformation

Six examples of work we have delivered, from data collection APIs and management systems to an enterprise AI platform.

Case List

AI and data projects in action

  1. Enterprise AI platform

    2025 — 2026
    Project overview
    ITSOLUTION built LF AI Workspace so LF employees could use AI in their daily work.
    What we built
    The workspace combines AI chat and AI agents. Its chat service answers questions using LF's internal data and the external data needed for analysis.

    Related product — ONDO AI ONTOLOGY
    Explore the knowledge capabilities of ONDO AI ONTOLOGY.

    How it is used
    LF employees use AI chat to ask about internal and external data and review the results. Agents tailored to each role support repetitive work and analysis.
    AI workspace example
    ⬡ ONDO AIDepartment usage 32% · Merchandising team demo account
    Period: Aug 2026 · Channel: offline · Category: outerwear
    Regular-price products
    Analyze the five lowest-selling stores under these conditions.
    graphify
    🧠 Reasoning
    I have checked the conditions. I will rank stores by sales, select the bottom five, and compare them with the same month last year.
    ✓ Queried internal sales data⌄

    The results are ready. Here is the summary.

    📊 Five lowest-selling stores · year-over-year

    RankStoreSalesYoY
    1NORDÉ Busan Seomyeon₩920K▼ 91.2%
    2NORDÉ Daegu Dongseong-ro₩2.1M▼ 68.4%
    3NORDÉ Gwangju Sangmu₩3.4M▼ 54.0%
    4NORDÉ Daejeon Dunsan₩4.8M▼ 22.6%
    5NORDÉ Incheon Songdo₩5.6M▲ 4.1%
    💡 graphify insight
    • Busan Seomyeon and Daegu Dongseong-ro are down more than 60% year over year. Check local market changes and operating issues first.
    • Incheon Songdo is the only store with year-over-year growth. Its operating approach may be worth sharing.
    Recommendation: review the lowest-performing stores on site and share practices from Incheon Songdo with other stores.
    Source: internal sales tableWithin authorized accessUnsupported answer blocked ✓
    Type a message...
    Internal data connection Deep research
    Available data · sales Inventory Reviews Search trends Customers

  2. Management information system

    2022–present
    Project overview
    We rebuilt and continue to operate a management information system to bring inconsistent business metrics and data collection into a common framework.
    What we built
    We aligned metric definitions and standardized data collection paths. We continue to oversee operations and reflect changes to the metrics.
    How it is used
    Teams across departments can view metrics based on the same definitions and see updated criteria reflected in the system.
    Management information system
    graphify MIS · Sales progress

    graphify MIS › Sales review › Monthly sales by channel

    Company-wide Reference: Aug 2026 · current month
    TOTALDirect retailFranchiseOnline
    Exclude exportsExclude internal transactions
    Daily sales trend This month · same day last month
    Annual sales trend Current year · previous year
    Monthly sales
    ₩9.68B
    ▲ 4.2% vs plan
    Cumulative sales
    ₩71.24B
    ▲ 6.1% YoY
    List-price ratio
    68.2%
    ▼ 1.1%p
    Realized price ratio
    61.5%
    ▼ 0.6%p
    Full-price sales share
    74.0%
    ▲ 2.3%p
    Inventory turnover
    3.2 times
    ▲ 0.2 turns
    By channelBy categoryBy seasonSales per store
    Sales by channel This month · same month last year
    ChannelSales · YoY
    1Direct online store₩3.84B▲ 7.8%
    2Franchise₩2.91B▲ 2.4%
    3Online store₩2.16B▲ 15.2%
    4Outlet₩620M▼ 3.1%
    5Pop-ups · other₩150M▲ 41.0%

    Next-generation MIS · consistent metric definitions across departments

  3. Customer analytics dashboard

    2023
    Project overview
    We built a dashboard to view customer data from multiple sources against enterprise-wide definitions.
    What we built
    The dashboard shows company-wide and divisional customer trends together and lets users compare different reference months.

    Related product — ONDO AI FORECAST
    Our customer analytics work helped shape how analysis is brought into everyday workflows.

    How it is used
    Users can compare customer trends by month in one place without compiling the data from scratch each time.
    Customer analytics dashboard
    graphify Analytics · Customer analysis
    Company-wide Reference: Jun 2026 · current month
    TOTALOfflineOnlineCross-channel
    Purchasing customers
    81K people
    ▼ 32.5% · −39K
    Repeat customers
    53K people
    ▼ 26.2% · −19K
    First-time buyers
    8,110 people
    ▼ 27.4% · -3,060
    Churned customers
    444K people
    ▲ 13.4%
    Member sales
    ₩29.29B
    ▼ 24.9% · −₩9.7B
    Purchase identification rate
    58.1%
    ▼ 0.4%
    Gender and age distribution Men 23,133 (28.5%) · women 58,060 (71.5%)
    ~29
    30–34
    35–39
    40–44
    45–49
    50–54
    55–59
    60–64
    MenWomen
    Customer journey First purchase → repeat purchase → churn
    First-time customers
    11K people → 53K repeat customers
    Reactivated customers
    17K people
    Value per purchase
    ₩232K
    Top stores By purchasing customers
    StoreCustomers · sales
    1NORDÉ online store39,793₩18.2B
    2NORDÉ Gangnam5,894₩3.1B
    3NORDÉ Hyundai Pangyo1,634₩900M
    4Atelier M Myeongdong1,210₩600M
    5Blanc Lotte Jamsil982₩500M
    Top products By sales
    Style code · productSales · customers
    1NDPK5A201IV · Cotton piqué polo₩88M586
    2NDSW5B118NV · Signature knit₩79M468
    3ATJU5B062BK · Tailored jacket₩70M124
    4BLPA5A235BG · Wide-leg slacks₩68M326
    5NDDR5B405WT · Pleated dress₩65M274

    Customer analytics · nine reports including brand summary, cross-purchases, buying patterns, and top customers

  4. Mobile management information system

    2024
    Project overview
    We built a mobile management system so teams could check key metrics in the field or on the move.
    What we built
    We rebuilt the existing management information system for mobile use.
    How it is used
    Teams can review the metrics they need and make informed decisions wherever they work.
    Mobile management information system
    G\
    HOMEMonthly salesOnline salesOnline inventory

    Mobile rebuild · view the same metrics in the field or on the move

  5. AI review summarization system

    2024
    Project overview
    We built a system to identify recurring customer feedback in growing volumes of product reviews and use it to guide improvements.
    What we built
    The system automatically summarizes and classifies product reviews in live operations. Its prompt design and LLM routing experience also informed query handling in ONDO AI ONTOLOGY.
    How it is used
    Teams see recurring feedback in summarized and classified reviews first, then use it to decide what to improve.
    ONDO AI review summary
    graphify Analytics · ONDO AI review summary
    NORDÉ 4,325 reviews · STCL 290 · since SS24
    By customerBy style code
    Score · overall rating
    4.7
    ★★★★★
    5 stars
    4 stars
    3 stars
    2 stars
    1 star
    Reviews · weekly trend
    Cumulative4,325reviews
    W-5 → W · rising over the last four weeks
    Sentiment · analysis
    4,325REVIEWS
    Positive 2,812 · 65%
    Negative 575 · 13.3%
    Neutral 938 · 21.7%
    [NORDÉ] Signature cotton piqué polo
    NDPK5A201IV · ONDO AI review summary
    Key purchase driversFabric feel · fit · color — “a weight that works year-round”
    What customers likedSoft feel, easy everyday fit, and little change after washing
    What customers dislikedRuns smaller than standard sizing — consider one size up
    AI-predicted score88.4 / 100 · high likelihood of repeat purchase

    ONDO AI summarizes and classifies 4,325 reviews · supports top-review views and reruns

  6. Search, social, and commerce data API

    2022
    Project overview
    We built a data collection API to bring external trend and price data into the enterprise.
    What we built
    We developed and launched APIs for collecting search, social, and commerce data.
    How it is used
    Teams use external trend and price data in internal analysis. This collection and processing experience also informed ONDO AI FORECAST.

    Case image

Could this work for your business too?

Let's explore an AI and data solution suited to your industry and the data you have.

Talk to us