Use Case Intelligence RSS Search use cases Search
IBM Education Spain

EUDE

Customer Service Automation · Enterprise Knowledge Search

EUDE needed to support a large online student population spread across time zones without forcing tutors to spend their time answering the same administrative and academic questions repeatedly.

Read the original story Explore all use cases
8 in test performance
9 in prediction accuracy
less than 20 seconds per response
more than 13,000 virtual students each year

Reported impact

Business outcome

EUDE showed that a governed AI co-tutor can improve student response times, help tutors focus on higher-value work, and support a more scalable online-learning experience.

  • Customer Experience
  • Productivity Improvement

Solution

EUDE built a virtual co-tutor called EDU on IBM Cloud using IBM watsonx.ai, IBM watsonx Assistant, and IBM Watson Discovery to support students and tutors across its online programs. The assistant accepts natural-language questions about academic, administrative, and logistical topics and uses a governed knowledge base to return immediate answers. Watsonx Assistant provides the conversational front end, watsonx.ai powers generative response behavior, and Watson Discovery extends the system's access to institutional knowledge, while IBM Cloud hosts the solution and keeps control of sources and school data inside the implementation. The initial one-week pilot with three dozen Digital Transformation students showed that the design could reduce routine tutor workload while maintaining fast responses for learners in many time zones. By shifting repetitive support questions to EDU, EUDE is turning generative AI into a scalable support layer around its teaching model.

Data flow

Students and tutors submit questions in natural language to EDU; watsonx Assistant routes the conversation, Watson Discovery retrieves relevant academic or administrative information, watsonx.ai composes the answer, and IBM Cloud serves the response back under EUDE-controlled data and content policies.

Solution architecture

4 components · 2 layers
  1. Compute
    • IBM watsonx.ai Provides the generative AI capabilities behind EDU's question-answering experience.
  2. Serving
    • IBM Cloud Hosts the EDU virtual co-tutor and the governed data and content used to answer questions.
    • IBM watsonx Assistant Acts as the conversational front end for student and tutor questions.
    • IBM Watson Discovery Supplies access to the broader knowledge base that EDU uses to answer academic and administrative questions.

Architecture clues

  • EUDE highlighted full control over response content, sources, and its own data.
  • The assistant is named EDU and supports both students and tutors.
  • The page mentions structured data access through text-to-SQL logic in the backend description.

Evidence from the source

"9 in prediction accuracy and 8 in test performance"
"EDU is a virtual co-tutor that is intended to offer real-time support to both students and tutors"
"The tool is based on IBM technology including IBM Cloud, IBM watsonx.ai, IBM watsonx Assistant and IBM Watson Discovery"
"designed to reduce the amount of time tutors need to spend on routine questions"
"the processing speed was less than 20 seconds per response"
Transparency Evidence & methodology 95/100 reference value · 92% confidence · 2 sources

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 value95/100
  • 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 scale5/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence92%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability23/25
    11 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 transparency9/10
    2 source references 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. IBM

    EUDE customer story

    First-party
    https://www.ibm.com/case-studies/eude
    Source type
    Vendor-published customer story
    Published
    May 14, 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
  2. LeadIQ

    EUDE Business School Company Overview, Contact Details & Competitors | LeadIQ

    Independent secondary
    https://www.leadiq.com/c/eude-business-school/5cf4dadb2000000e01158705

    EUDE Business School has approximately 394 employees.

    Source type
    Structured company profile
    Supports
    • Company size

Date evidence

Not separately sourced Industry, Region. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
IBM Oct 28, 2024 Tutore Education Poland Tutore needed a way to answer large volumes of repetitive student and parent questions around the clock because fast growth was overwhelming support teams and 24x7 manual coverage would have been too expensive. 90,000+ messages across 40,000 conversations in first nine months Customer Service AutomationEnterprise Knowledge Search Actionbot · IBM watsonx Assistant IBM Jul 10, 2024 The University of Auckland Education New Zealand The University of Auckland needed to handle surging and constantly changing student questions during the shift to virtual learning, but outdated search and support processes made it hard to deliver timely, accurate, and… 40% improvement in first-time resolution Customer Service AutomationEnterprise Knowledge Search IBM Watson Discovery · IBM watsonx Assistant IBM Apr 19, 2024 GK Cloud Solutions Private Limited Education India GK Cloud Solutions needed a scalable way to personalize corporate training, answer learner questions in context and keep support available around the clock without incurring the high cost and operational burden of… 10% reduction in time spent completing training programs Customer Service AutomationEnterprise Knowledge Search IBM Cloud · IBM Watson Discovery · IBM watsonx Assistant