Use Case Intelligence RSS Search use cases Search
Microsoft Education Indonesia

Universitas Terbuka

Document Processing · Enterprise Knowledge Search · System Migration

Indonesia's Universitas Terbuka (UT), with over 525,000 active students and growing, struggled to provide timely tutor support, risking student engagement, satisfaction, and retention.

Read the original story Explore all use cases
The AI tutor enhances student grades and engagement by providing more comprehensive support 24 hours a day.
The tutor currently supports 500 classes
The tutor currently supports 500 classes and some 100,000 students.
engagement by providing more comprehensive support 24 hours a day.

Reported impact

Business outcome

The tutor currently supports 500 classes and some 100,000 students.

  • Customer Experience
  • Productivity Improvement
  • Revenue Growth
  • Risk Reduction

Solution

Universitas Terbuka used Azure OpenAI Service, Azure AI Foundry, Azure AI Document Intelligence to move core workloads off legacy infrastructure and into a more scalable Azure operating model. Application, integration, and data services were rehosted or re-platformed so teams could standardize deployment, improve resilience, and create a foundation for newer analytics or AI capabilities. It also connects with surrounding systems such as Microsoft Word, Learning management system, which lets the new Azure-based workflow fit into existing operations rather than standing apart from them. The tutor currently supports 500 classes and some 100,000 students.

Data flow

Content and operational context are prepared in Azure AI Document Intelligence, passed to Azure OpenAI for generation or extraction, stored in Azure Cosmos DB, and returned through the user-facing application to employees or customers with grounded responses.

Solution architecture

5 components · 4 layers
  1. Ingest
    • Azure AI Document Intelligence Extracts text, layout, and document fields before downstream AI or analytics processing.
  2. Compute
    • Azure OpenAI Service Runs large language model inference for summarization, extraction, conversational AI, and grounded answers.
    • Azure Kubernetes Service Hosts scalable APIs, microservices, and model-serving workloads in containers.
  3. Storage
    • Azure Cosmos DB Persists low-latency application data, conversation state, or operational records.
  4. Orchestration
    • Azure AI Foundry Provides the managed environment for model orchestration, experimentation, and responsible AI operations.

Architecture clues

  • 100,000 students
  • 500 classes
  • Extracts text and document structure prior to downstream AI processing.
  • Runs scalable containerized services on Azure Kubernetes Service.
  • Uses Azure OpenAI for grounded generation or large-scale extraction workloads.

Evidence from the source

Azure OpenAI Service provided that scalability," says Dimas Agung Prasetyo, M.S., currently Head of the Undergraduate Program in Data Science for Universitas Terbuka.
Dimas Agung Prasetyo, M.S., Head of the Undergraduate Program in Data Science, Universitas Terbuka In 2023, the university used Azure AI Foundry to build an AI tutor accessed through the school's customized Moodle LMS, which students use...
Indonesia's Universitas Terbuka (UT), with over 525,000 active students and growing, struggled to provide timely tutor support, risking student engagement, satisfaction, and retention.
The tutor currently supports 500 classes and some 100,000 students.
UT used Microsoft Azure OpenAI Services and Azure AI Foundry to build an AI tutor that delivers accurate, curriculum-aligned responses and streamlines student assessment.
Transparency Evidence & methodology 92/100 reference value · 87% 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 value92/100
  • 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 specificity12/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    5 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence87%
  • 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
    5 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 specificity8/10
    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. Microsoft

    Universitas Terbuka customer story

    First-party
    https://www.microsoft.com/en/customers/story/20284-universitas-terbuka-azure-blob-storage
    Source type
    Vendor-published customer story
    Published
    Dec 13, 2024
    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 Dec 13, 2024 · Microsoft · 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
Microsoft Oct 18, 2024 Orbital Witness Software / SaaS United Kingdom "At the time it was a difficult decision with an uncertain outcome. But, with 70 percent time savings when performing due diligence, our customers want these tools at their… Document ProcessingEnterprise Knowledge Search Azure AI Vision · Azure App Service · Azure OpenAI Service Microsoft Oct 15, 2026 Bar-Ilan University Education Israel Students who miss lectures struggle to reconnect new lessons with prior material when course information is spread across notes, recordings, slides, and readings, and lecturers need a reliable way to answer routine… 71 courses Document ProcessingEnterprise Knowledge Search Azure AI Services · Microsoft Azure · Microsoft Copilot Studio Microsoft Nov 17, 2023 Wichita Public Schools Education United States Dyane Smokorowski, Coordinator of Digital Literacy at Wichita Public Schools, believes that a major part of every educator’s job is breaking down would-be barriers between students and a great education. Using AI as an… Document ProcessingEnterprise Knowledge Search Microsoft Copilot