Build
Tools that put research into practice — software, platforms, and pipelines.
The Lab’s build pillar produces working software: virtual TAs, exam-creation tools, AI-grading pipelines, judicial chambers tools, course-material repositories, simulation environments. Default is open source.
Code lives at github.com/ai-teaching-lab.
Projects in Build
Workstreams the Lab is running under the build pillar — including projects that span multiple pillars.
Exam Grader
Calibration-based AI grading for law-school essay exams — deployed against Polk's Spring 2026 IP class.
Course Materials
An extraction primitive: turn the messy artifacts of a real course — PDFs, slide decks, casebook excerpts, syllabi — into clean structured text that downstream tools can use.
Casebook Builder
Curate and edit cases into custom course casebooks — pilot deployment with Ted Ruger's Spring 2027 Legislation class.
Exam Taker
Wave 2 of the AI Final Exam Project — putting current models against real Penn Carey Law finals and reporting what they can and can't do.
Course-Website Tooling
Generalize the Legal Education at Model Velocity microsite into reusable templates the Lab and others can deploy quickly.
Essay Creator
Generate assessment-grade essay exams — issue spotters and fact-pattern questions — with rubrics built for AI-assisted grading.
MCQ Creator
Generate law-school multiple-choice questions with built-in distractor validation and psychometric quality controls.
Heron — Virtual TA Slackbot
Pedagogy infrastructure: a Slackbot that serves as a 24/7 virtual teaching assistant for course use.
Class Simulations
AI-driven simulations built around the actual class problems law students work through each week — starting with patent law.
Newsletter Automation
Build the pipeline that produces the Lab's monthly AI newsletter — automated collection, editorial workflow, Substack distribution.
Training Materials
Produce a complete AI training package for legal-education audiences — and pitch a cross-Penn version with collaborators.