{"resourceId":"hkbu-aita-course-grounded-ai-tutor-100-courses-20261030","versions":[{"version":"external-90e3ec5c3d61ad0059f84299bd230aa9686483b555408608a1da7cde769d03be","resource":{"id":"hkbu-aita-course-grounded-ai-tutor-100-courses-20261030","title":"HKBU says its course-grounded AITA tutor, integrated with Moodle, is used in more than 100 courses with over 3,000 registered users across HKBU and CUHK","organization":"Hong Kong Baptist University (Department of Computer Science) with The Chinese University of Hong Kong","sector":"Higher education AI tutoring and learning analytics","geography":"Hong Kong SAR, China","publishedAt":"Discover HKBU, 30 October 2026","publicationDate":"2026-10-30","eventDate":null,"sourceName":"Hong Kong Baptist University","sourceLabel":"Developer institution feature (self-reported)","sourceUrl":"https://www.hkbu.edu.hk/en/whats-new/discover-hkbu/2026/Oct-2026/personalised-ai-tutor-to-help-students-learn.html","evidenceClass":"vendor-claim","outcomeClass":"emerging","topics":["knowledge-work","developers-agents","infrastructure"],"finding":"HKBU describes AITA, a course-materials-driven AI tutor led by its Computer Science department with CUHK collaborators. It integrates with Moodle, generates summaries and mind maps, aligns lecture audio with slides, and answers student questions on highlighted slide text with step-by-step answers and slide references, using course-oriented retrieval-augmented generation that the team says reduces hallucinations. An agent interprets questions and creates assessment items; quizzes have automated grading, and a learning analytics engine gives instructors recommendations. HKBU says AITA is used in more than 100 courses with over 3,000 registered users at HKBU and CUHK and more than 20 other institutions, and will expand with UGC funding.","sledRelevance":"A scaled, LMS-integrated, course-grounded tutor design that contrasts with general-purpose chatbots; useful as an architecture reference, though without outcome evidence.","evidence":"Developer-reported features, adoption counts, awards and two student testimonials; no measured learning results.","architectureImplications":"Course-oriented RAG over uploaded materials, Moodle integration, slide-referenced answers, an instruction agent and a learning analytics engine.","governanceImplications":"Instructor-facing analytics and auto-generated assessments raise questions about instructor review of generated questions and grading.","securityPrivacyImplications":"Real-time engagement tracking implies student activity data collection; the article does not describe data handling or model hosting.","caveats":"Self-promotional source; \"promising results\" not quantified; competition awards are not evaluations; Hong Kong context.","streamIds":["student-success"],"roles":{"sales":"Sales framing: HKBU's AITA shows the design many campuses ask about: a tutor grounded in each course's own slides and recordings, inside the LMS, with references back to the source slide. Use it to frame discovery on course-grounded tutoring versus general chatbots. A bounded engagement could pilot a comparable design in a few courses with a proper evaluation. Do not cite learning benefits; HKBU reports adoption counts and testimonials, not measured results.","engineering":"Engineering framing: the architecture is course-scoped retrieval over uploaded materials, Moodle integration, slide-anchored answers, an instruction agent that generates questions, and engagement analytics. Check content ingestion for slides and audio, per-course access control, model hosting and where student activity data lives. Proof of value should measure grounded-answer accuracy and citation correctness on real course questions, quiz-item quality reviewed by instructors, and latency at course scale.","delivery":"Delivery framing: delivery depends on faculty uploading materials and reviewing generated quizzes, so adoption support matters as much as the software. Work includes onboarding instructors, setting review rules for auto-graded items, and defining how analytics recommendations reach teaching staff. The developer team and teaching centre share ownership. Define outcome measures before scaling, since HKBU's article offers usage counts but no evidence of learning change."},"roleDetails":{"sales":{"customerProblem":"General-purpose AI tools lack course context and give impersonal, possibly wrong answers.","stakeholders":["Teaching and learning center","Computer science or IT developers","Faculty","Learning analytics team","Funding body or grants office"],"discoveryQuestions":["Do you want tutoring grounded only in course materials?","Who will upload and maintain course content?","How will instructors review generated quizzes?"],"valueHypothesis":"Interpretation: course-grounded tutoring with slide references may reduce wrong answers and keep students tied to course materials.","potentialEngagement":"Evaluated pilot of a course-grounded tutor in a few courses with accuracy and engagement measures.","unsupportedClaims":["Learning gains","Reduced hallucination rate without testing","Transferability of adoption counts"]},"engineering":{"fit":"Institutions with an LMS such as Moodle and developer capacity or a comparable product.","architectureIntegration":"Course-scoped RAG over slides and audio, LMS integration, slide-anchored answers, question-generation agent and analytics engine.","prerequisites":["Course content in machine-readable form","LMS integration rights","Model hosting decision"],"constraints":["Content upload burden","Hong Kong funding and context","Unknown hosting and data terms"],"security":"Enforce per-course access control and document retention of student questions and engagement data.","proofOfValue":["Grounded-answer accuracy on real questions","Citation-to-slide correctness","Instructor-rated quiz item quality"]},"delivery":{"work":"Onboard instructors, ingest course materials, set review rules for generated quizzes and analytics, and run an evaluated pilot.","dependencies":["Faculty content preparation","Developer or vendor support","LMS administrators"],"ownership":"Teaching and learning center with the developer team.","skillsAdoption":"Instructor training on content upload, quiz review and analytics; student guidance on checking slide references.","governanceCheckpoints":["Data handling review before launch","Instructor sign-off on generated assessments","Outcome evaluation before scale-up"],"acceptanceCriteria":["Proposed: answer accuracy above an agreed threshold on sampled questions","Proposed: all auto-graded items instructor-reviewed","Proposed: pre-registered outcome measures"],"risks":["Unreviewed generated assessments","Engagement surveillance concerns","Adoption without evidence"]}},"retrievedAt":"2026-10-31T03:20:37Z","enrichedAt":"2026-10-31T03:24:06Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Multilingual spoken questions and audio-slide alignment may help some learners; accessibility testing is not reported.","procurementImplications":"Publicly funded university-built tool (Fund for Innovative Technology-in-Education) rather than a commercial purchase; multi-university deployment planned.","operatingModelImplications":"Interpretation: a built-in-house tutor shifts maintenance, content upload and support to faculty and the developer team.","sourceVerification":{"openedUrl":"https://www.hkbu.edu.hk/en/whats-new/discover-hkbu/2026/Oct-2026/personalised-ai-tutor-to-help-students-learn.html","referenceExcerpt":"AITA is already adopted by more than 100 courses, with more than 3,000 registered users from HKBU and CUHK","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}