How UT Austin built a generative AI tutor platform on AWS
Building on a commitment to using innovative technologies to enhance the learning experience, the University of Texas at Austin collaborated with Amazon Web Services to develop UT Sage, a faculty-guided generative AI tutor platform. UT Sage provides conversational course-related support on demand while aligning with responsible AI frameworks and preserving the faculty-student connection. Faculty can create customized virtual tutors aligned with course material, and students interact with them through Socratic dialogue to deepen understanding rather than just retrieve answers.
- Organization
- University of Texas at Austin
- Industry
- Education
- Location
- United States
- Published
- July 2025
Reported outcomes
Strategic outcomes
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- University of Texas at Austin
- Provider
- AWS
- Maturity
- Unknown
- Linked source
- AWS Public Sector Blog
No explicit deployment-stage evidence found.
Primary read
Use case focus
Showing 3 of 4
- 1AI Tutor
- 2Student Support
- 3Personalized Learning
- Provide scalable personalized tutoring and learning support while managing faculty workload.
- Deliver consistent, high-quality assistance aligned with course material and academic integrity.
- Extend student support beyond the classroom without replacing faculty-student relationships.
- The university built UT Sage, a faculty-guided generative AI tutor platform on AWS.
- The architecture uses Amazon Bedrock for foundation model access and generative AI capabilities, Amazon Textract to extract and process course materials, AWS Step Functions for serverless orchestration, Amazon OpenSearch Service for storage and retrieval, Amazon Cognito for authentication, Amazon ECS for scalable application services, Amazon S3 for course materials, and Amazon API Gateway for frontend and API integration.
- UT Sage uses a lightweight agentic AI approach that dynamically accesses a knowledge base of course material and relevant tools to answer student questions.
- The system grounds responses in curated, instructor-provided materials and uses prompts to keep tutors focused and responsible.
- After about a year of ideation, development, and testing, UT Sage is in open beta.
- Early feedback from students and instructors has been overwhelmingly positive.
- The university expects the platform to roll out across hundreds of courses.
- The solution aims to reduce the time and effort required to design student-centered, high-quality course materials.
- Planned LMS integrations and instructor dashboards are intended to improve teaching insight and learning support.
Architecture
AWS reference architecture centered on Amazon Bedrock, Amazon Textract, AWS Step Functions, Amazon OpenSearch Service, Amazon Cognito, Amazon ECS, Amazon S3, and Amazon API Gateway to power a faculty-guided AI tutoring platform grounded in course materials.
Sources & evidence1
- Customer explicitly identified
- Technical implementation details available
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Was this useful?
Community
Comments
Loading comments...