TLDR: The University of Texas at Austin, in collaboration with Amazon Web Services (AWS), has launched UT Sage, a generative AI tutor platform designed to provide personalized, on-demand learning support to its 52,000 students. This initiative aims to enhance academic experiences by fostering critical thinking through Socratic dialogue, while maintaining faculty oversight and adhering to responsible AI frameworks.
The University of Texas at Austin (UT Austin) has unveiled UT Sage, an innovative generative AI tutor platform developed in partnership with Amazon Web Services (AWS). This platform is set to revolutionize personalized learning support for the university’s approximately 52,000 students across 19 colleges and schools. The initiative addresses the growing presence of generative AI in education, aiming to integrate these tools responsibly while safeguarding academic integrity.
UT Sage is designed to provide conversational, course-related support on-demand, aligning with established learning sciences and UT Austin’s responsible AI adoption framework. Kasey Ford, AI designer and product owner for UT Sage at UT Austin, stated, “Our goal was to create a platform that promoted evidence-based pedagogical practices that faculty could trust and that students could use to support their academic goals.” The platform allows faculty to create customized virtual tutors aligned with their specific course materials, engaging students through Socratic dialogue to promote durable skills like critical thinking, rather than simply providing direct answers.
Scalability was a key consideration during development, as UT Austin sought a solution flexible enough to serve a wide array of disciplines. To achieve this, UT Austin collaborated with the AWS Generative AI Innovation Center, an acceleration team that provides hands-on support in building and deploying generative AI solutions. Ladd Hanson, enterprise cloud architect at UT Austin, highlighted the impact of this collaboration, noting, “One of the things that made working with the AWS Generative AI Innovation Center so impactful was that it wasn’t just high-level advising—it was hands-on-keyboard support.” Robby Milletich, senior applied scientist at AWS, praised UT Austin’s commitment to rigorous user testing, which significantly informed the platform’s features.
The technical architecture of UT Sage leverages several AWS services, including Amazon Bedrock for foundation models, Amazon Textract for data extraction from course materials, AWS Lambda for backend orchestration, Amazon DynamoDB and Amazon OpenSearch Service for data storage and retrieval, Amazon Cognito for authentication, Amazon Elastic Container Service (Amazon ECS) for scalable application services, Amazon Simple Storage Service (Amazon S3) for course material storage, and Amazon Amplify for frontend development. The platform employs a lightweight agentic AI approach, dynamically accessing a knowledge base of instructor-provided course materials to answer student questions and guide them through Socratic-like interactions.
Security and responsible AI use were paramount in the development of UT Sage. Each topic tutor is grounded in curated, instructor-provided materials, with system prompts carefully designed to maintain domain focus and prevent off-topic or inappropriate responses. After approximately a year of ideation, development, and testing, UT Sage is currently in open beta, with overwhelmingly positive early feedback from both students and instructors.
Also Read:
- Instructure’s IgniteAI on AWS: Revolutionizing Education with Generative AI
- AWS and Udacity Launch 2025 AI and Machine Learning Scholars Program
Looking ahead, UT Sage is scheduled for a broader rollout across the university in Fall 2025, with planned integrations into UT Austin’s learning management system (LMS). Future enhancements include an instructor dashboard to provide aggregate data on student questions, offering insights to inform in-class teaching. Julie Schell, assistant vice provost and director of the Office of Academic Technology, remarked, “We believe UT Sage may be one of the first scalable, research-based virtual instructional designers in higher education. This collaboration with AWS marks a significant step in our journey to accelerate education in the AI era.”
