Carnegie Mellon University
School of Computer Science  ›  TEEL Lab  ›  Projects

Sail() Platform

2014 → Today
Developmental Project; Research 

The Sail() Platform represents TEEL lab’s 10+ years of research and experience in project based learning and data informed teaching. With 2000+ new learners per year, and ~100 active contributors and collaborators, the platform is now in its second major release, hosting a suite of learning pathways in cloud computing, data science, and AI/ML.

Visit the Sail() Platform website to learn more and request a demo.

Sail platform

Carnegie Mellon Accenture Center of Excellence for AI

2025 → Today
Academic-Industrial Partnership

The Carnegie Mellon Accenture Center of Excellence for AI (ACE-AI) is a collaboration focused on addressing critical challenges in workforce development. The center is built on three pillars: AI for coaching and tutoring, AI for training content development, and AI for learning analytics. ACE-AI is led by a multidisciplinary team of experts from Carnegie Mellon University, including professors from Computer Science, Human-Computer Interaction, and the Heinz College of Information Systems and Public Policy. The center develops innovative solutions for personalizing training experiences, creating AI agents that serve as tutors, couches, and career counselors, automating assessment of learner capabilities, and generating modular training content. The work directly addresses the growing demand for technology workforce development.

Learn more here: ACE-AI Collaboration

Project ACE AI

AI Technicians

2020 → Today
Rapid Occupational Training Program; Research; Academic-Government Partnership

The AI Technicians program at Carnegie Mellon University offers an intensive 8-month workforce training solution that bridges the critical gap between AI scientists and end users. Using immersive project-based learning, our program develops technical professionals who can drive the full AI cycle from problem understanding to deployment and maintenance.

Learn more here: AI Technicians Program

AI technicians

AI Literacy for Community Colleges

2023 → Today
Curriculum Development; NSF-Funded Research

AI User is an introductory AI literacy curriculum, focusing on having learners collaborate with AI-enabled systems so they can effectively utilize these systems in their careers. AI User is a curriculum that can be integrated into any course, as AI is changing the workforce across many disciplines. Each of the 8 units is taught within a relatable context, and instructors can select the modules that are relevant to their course. AI User teachs foundational AI concepts to non-STEM students with a high-school education using interactive no-code projects based on real-world scenarios.

Learn more here: AI User for Community Colleges

AI user project

FoW: Future of Work

2022 → Today
Developmental Project; Research

As part of a broader effort to expand access to digital economy jobs, we are testing intelligent tutoring systems and collaborative learning activities in community college IT courses with partners at CMU and CCAC. Guided by the Knowledge-Learning-Instruction (KLI) framework, we match each activity type with the most effective instructional technology to support fluency, reasoning, and deep understanding. These experiments take place in real classrooms and capstones, allowing us to study their impact on both academic performance and job readiness. The goal is to help students master key skills more efficiently and transition successfully into IT careers.

Future of work

OPE: Online Programming Experience

2019 → Today
Research Resource; Collaborative Learning Platform

The Online Programming Experience (OPE) is a collaborative activity offered through our Sail() platform in partnership with Carolyn Rosé's lab. Students work in small teams within shared Jupyter notebooks, guided by a chatbot that introduces problems, manages time, and prompts role-switching inspired by Mob Programming. Designed to support equitable participation, OPE ensures all students engage deeply with each learning objective. It also serves as a research platform, revealing that structured collaboration and reflection can boost learning outcomes, communication, and confidence for all students.

ope.png

Interactive Smart Learning Content

2024 → Today
Academic Collaboration

TEEL Lab closely collaborates with University of Pittsburgh’s Personalized Adaptive Web Systems Lab (PAWS) in exploring how can a range of user modeling, adaptation and personalization technologies augment learning in community college introductory programming classes. The collaboration focuses on adaptive practice activities that provide a bridge between conceptual content and Sail() hands-on projects. The goal is to provide flexible content that supports learners with various backgrounds and needs.

Interactive smart learning content

PlantD: Data Pipeline Wind Tunnel

2021 → 2024
Developmental Project; Research

PlantD is an open-source tool developed with Honda Research Institute to help organizations evaluate and improve cloud data pipelines. Acting like a "wind tunnel," it sends synthetic data through a pipeline to measure performance and cost under simulated future conditions. Engineers can identify bottlenecks, compare designs, and forecast scalability, while business users can run "what if" scenarios to inform strategic decisions. By translating technical performance into business outcomes, PlantD bridges engineering and planning.

project-plantd.png

AIDEN

2024 → Today
Developmental Project

AIDEN is a prototyped LLM-based Q&A agent for teaching assistants (TAs) in CMU’s Cloud Computing course. AIDEN received a live feed of students' questions from the Q&A forum used by the course, and provides TAs with a draft response based on previously frequently asked questions. AIDEN has been integrated with both Slack and Piazza.

Aiden

Bazaar

2016 → Today
Research Resource

Bazaar is a publicly available architecture for orchestrating conversational agent-based support for group learning. It is a powerful tool for facilitating research in collaborative learning. It hosts a library of reusable behavioral components that each trigger a simple form of support. More complex supportive interventions are constructed by orchestrating multiple simple behaviors. Its flexibility and simplicity mean it can be used to very rapidly develop platforms for investigating a wide range of important questions within the design space of dynamic support for collaborative learning.

Bazaar

LOGAN: Cheat Checking Facilities

2012 → Today
Developmental Project; Learning Analytics

LOGAN is a cheat-checking facility that uses student assignment submissions and logs of quiz-taking behaviors to assemble reports used by instructors to find academic honesty violations and build evidential reports about the incidents. It is used in our courses at CMU.

Logan

LightSide Workbench

2012 → Today
Research Resource; Natural Language Processing

The open-source LightSide platform, including the machine-learning and feature-extraction core as well as the researcher's workbench UI, has been and continues to be funded in part through Carnegie Mellon University, in particular by grants from the National Science Foundation and the Office of Naval Research. We make the LightSide research platform freely available for research and education. In exchange, we ask that you provide us with basic information about who you are and how you're making use of LightSide's capabilities.

Lightside Workbench

DiscourseDB

2015 → Today
Research Resource; Research Data Infrastructure

DiscourseDB is an NSF funded data infrastructure project designed to bridge data sources from multiple platforms for hosting those learning experiences. Our vision is to provide a common data model designed to accommodate data from diverse sources including but not limited to Chat, Threaded Discussions, Blogs, Twitter, Wikis, and Text messaging. We will make available analytics components related to constructs including role taking, help exchange, collaborative knowledge construction, showing openness, taking an authoritative stance, attitudes, confusion, alliance and opposition. In enabling application of such metrics across datasets from multiple platforms, research questions related to the mediating and moderating effect of these processes and state measures on information transfer, learning, and attrition can be conducted, building on the earlier research of our team.

DiscourseDB

Social Recommendation

2014 → 2015
Research Resource; Collaborative Learning Platform

Massive Open Online Courses have experienced a recent boom in interest. Problems students struggle with in the discussion forums, such as difficulty in finding interesting discussion opportunities or attracting helpers to address posted problems, provide new opportunities for recommender systems. We developed a social recommendation technology to support help seekers in MOOC discussion forums implemented using a context-aware Matrix Factorization model to predict students' preferences for answering a given question. This recommendation framework allows for this two-way recommendation.

Social recommendation

Progressive Insurance

2023 → 2024
Rapid Occupational Training Program; Academic-Industrial Partnership

The TEEL lab provided workforce training in cloud administration for two cohorts of Progressive Insurance employees, during the years of 2023 and 2024. A total of 19 individuals completed the training, and transitioned to new positions within the company. The training was in collaboration with Community College of Allegheny County and Sponsored by Microsoft Azure.

Progressive insurance partnership