Normalized claim
Quantified impact: 99% increase
Student class satisfaction increased to 99%.
UNSW revolutionizes student engagement with AI-powered QBot
Use case typeStudent supportUpdated Jun 13, 2026
The University of New South Wales (UNSW) in Australia implemented an AI-powered Question Bot (QBot) to improve student engagement and reduce repetitive tasks for teaching staff, particularly in remote learning scenarios. QBot integrates with Microsoft Teams to assign student questions to relevant teaching assistants and builds a knowledge base of Q&A pairs for future queries. It leverages Microsoft Stream to search video transcripts and provide relevant content and uses Microsoft Custom Vision to recognize student worksheets, streamlining support for academic materials. The solution has fostered a highly engaging AI-driven learning community. The initiative led to a significant increase in class satisfaction and greater availability of academic support, 24x7, while alleviating teaching staff workload. The transformation effort forms part of broader digital and AI innovation at UNSW. QBot is open-sourced and aims to create a seamless, collaborative educational environment that empowers both students and educators. By automating routine support, the university has enhanced efficiency and improved overall learning outcomes. The project highlights Microsoft's ongoing partnership with higher education to realize the vision of data-driven, inclusive, and accessible learning experiences.
- Organization
- University of New South Wales
- Industry
- Education
- Location
- Australia
- Published
- March 2020
Reported outcomes
+99%
quantified impactCustomer experience
Strategic outcomes
Customer experience & trustImproved student engagement and participationCustomer experience & trustEnabled 24x7 academic supportCost efficiencyReduced repetitive support workloadNew product / capabilityBuilt searchable Q&A knowledge base
Catalog median for customer experience deployments: +25% across 53 reported metrics. Compare benchmarks →
Why do we believe this?Outcome claims, sources, and evidence checks
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- University of New South Wales
- Provider
- Microsoft
- Maturity
- Production
- Linked source
- news.microsoft.com
Deployed QBot, an AI-powered Question Bot integrated into Microsoft Teams
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 4
- 1AI-powered Student Q&A Automation
- 2Automated Academic Support Knowledge Base
- 3Intelligent Lecture Content Search with Video Transcript Indexing
- Low student engagement in remote classes.
- Teaching staff burdened by repetitive queries.
- Lack of 24x7 academic support for students.
- Inefficient searching and retrieval of relevant educational content.
- Difficulty recognizing and managing diverse student work formats.
- Deployed QBot, an AI-powered Question Bot integrated into Microsoft Teams.
- QBot automatically assigns questions to the appropriate teaching assistants and builds a searchable Q&A knowledge base.
- Integrated Microsoft Stream to index and search lecture video transcripts.
- Applied Microsoft Custom Vision to recognize student worksheets from images.
- Created an engaging, AI-driven learning community with self-service support available 24x7.
- Student class satisfaction increased to 99%.
- Academic help became continuously available (24x7).
- Teaching staff saw a reduction in workload from repetitive support tasks.
- Improved student engagement and participation in online learning.
Architecture
QBot is integrated into Microsoft Teams and uses Microsoft Stream to search and index video transcripts for relevant lecture material. Microsoft Custom Vision is used to process uploaded images of student worksheets, and the Microsoft Bot Framework routes questions to the appropriate teaching staff while maintaining a knowledge base of Q&A pairs.
Sources & evidence1
Evidence: Medium65/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Independent source available
- Quantified outcome available
- Technical implementation details available
Type: News ArticlePublished: Mar 26, 2020Publisher: news.microsoft.comEvidence: SecondaryConfidence: Low
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
AI patterns
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.