Microsoft Education Israel Company newsroom

Bar-Ilan University

Document Processing · Enterprise Knowledge Search

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 course questions and support exam preparation without replacing teaching.

71 courses
about 2,400 students
about three hours a day studying after lectures, compared with five to six hours previously
another 100 courses

Reported impact

Business outcome

Students can search and summarize course content, generate self-tests, and study more independently; one student reduced post-lecture study time to about three hours from five to six. Lecturers report fewer routine and administrative questions and less exam anxiety among students. In one course, the lecturer said the average final score was three percentage points higher than in previous years, while noting the cohort may also have been stronger.

  • Customer Experience
  • Productivity Improvement

Solution

Bar-Ilan University piloted a multilingual learning agent inside its Moodle learning platform to turn course repositories into searchable study support. Teaching staff upload recorded lectures, transcripts, presentations, articles, research papers, and recommended reading; those materials form the bot’s exclusive grounding corpus. KPMG and OpenApp developed the agent with Microsoft Copilot Studio, and Azure AI Services powers natural-language search, summarization, and quiz-style interactions over the course content. The service runs in BIU’s secure Microsoft Azure environment, keeping the experience inside the university’s managed cloud boundary. Students can ask questions in Hebrew, Arabic, or English to find lecture topics, generate summaries, and test themselves, while lecturers improve answer quality by refining course materials, adding fuller explanations, and feeding complete lecture transcripts into the system.

Data flow

Lecturers upload recorded lectures, transcripts, presentations, articles, research papers, and recommended reading into BIU's Moodle-based course environment. Microsoft Copilot Studio orchestrates an agent grounded only on that corpus, Azure AI Services processes student questions in Hebrew, Arabic, or English, and the resulting topic lookups, summaries, and quizzes are returned to students through Moodle inside BIU's secure Microsoft Azure environment.

Solution architecture

4 components · 4 layers
  1. Compute
    • Azure AI Services Processes natural-language queries and generates grounded summaries and quiz interactions over course materials.
  2. Serving
    • Moodle Hosts the learning agent within BIU's course environment where students access search, summaries, and quizzes.
  3. Orchestration
    • Microsoft Copilot Studio Provides the agent framework KPMG and OpenApp used to build and configure the learning assistant.
  4. Uncategorized
    • Microsoft Azure Provides the secure cloud environment in which the university operates the learning agent and its content.

Architecture clues

  • Available in Hebrew, Arabic and English.
  • Grounded exclusively in course materials uploaded by BIU teaching staff.
  • Initial rollout covered 71 courses and about 2,400 students, with expansion planned to another 100 courses in the 2026/27 academic year.
  • Runs in the university's secure Microsoft Azure environment.

Evidence from the source

"At the finals in August, the average score among his 50 or so students was three percentage points higher than in previous years."
"Available in Hebrew, Arabic and English, the agent will be rolled out to another 100 courses in the first semester of the 2026/27 academic year."
"In February, BIU piloted an AI agent on its Moodle learning platform that helps students search and summarize course materials using natural language queries, turning these vast resources into learning support."
"Powered by Azure AI Services and developed by KPMG and OpenApp using Microsoft Copilot Studio, the agent is grounded exclusively in course materials uploaded by BIU's teaching staff, including recorded lectures, transcripts, presentations and articles."
"She now spends about three hours a day studying after lectures, compared with five to six hours previously."
"The agent operates in the university's secure Microsoft Azure environment."
"The pilot covered 71 courses and about 2,400 students at BIU, one of Israel's leading public research universities with over 20,000 students in Ramat Gan, near Tel Aviv."
Transparency Evidence & methodology 70/100 reference value · 93% 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 value70/100
  • 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 impact0/25
    0 metrics describe measurable impact.
  • Deployment scale5/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence93%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability25/25
    12 of 12 key fields link to a named source.
  • Direct evidence20/20
    7 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency10/10
    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

    Missed a lecture? This AI agent at Bar-Ilan University helps students catch up - Source EMEA

    First-party
    https://news.microsoft.com/source/emea/features/missed-a-lecture-this-ai-agent-at-bar-ilan-university-helps-students-catch-up/
    Source type
    Vendor-published customer story
    Published
    Oct 15, 2026
    Supports
    • Customer
    • Region
    • Company size
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • Business outcome
    • Metrics
    • Architecture
    • Publication date

Date evidence

  • Published on source page Oct 15, 2026 · Bar-Ilan University · First-party
    Open date source
Not separately sourced Industry. Treat these normalized attributes as lower-confidence until a dedicated source is added.