Penn Carey Law AI Project / Projects
Projects
The Project's active work, organized by cluster.
The Project organizes its work into clusters of related projects. Each cluster shares infrastructure, owners, or a common audience — and each project inside a cluster has its own scope, status, and pillar alignment.
No projects match this filter.
Assessment Tools
04AI on both sides of the law-school exam — taking, grading, and helping faculty write better questions.
Exam Grader
Calibration-based AI grading for law-school essay exams — deployed against Polk's Spring 2026 IP class. ActiveExam Taker
The AI Final Exam Project — can current AI pass real Penn Carey Law finals when its work is graded blind, on the curve, by the faculty who wrote the exams? Wave 1 results are in. ActiveEssay Creator
Generate assessment-grade essay exams — issue spotters and fact-pattern questions — with rubrics built for AI-assisted grading. ActiveMCQ Creator
Generate law-school multiple-choice questions with built-in distractor validation and psychometric quality controls. ActiveTeaching Tools
05The connective tissue of a course — extraction, casebooks, virtual TAs, simulations, and the templates that hold them together.
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. ActiveCasebook Builder
Curate and edit cases into custom course casebooks at a fraction of the commercial cost — faculty pilots in Torts and Patents (Fall 2026) and Legislation (Spring 2027). ActiveCourse-Website Tooling
Generalize the Legal Education at Model Velocity microsite into reusable templates the Project and others can deploy quickly. PlanningHeron — A Course-Bounded Virtual TA
A virtual teaching-assistant chatbot bound to one course's materials: it answers students in Slack from the assigned readings, with citations. Plus the argument that faculty should consider building these to govern the AI students already use. Spring 2026 results and a draft paper. ActiveClass Simulations
AI-driven simulations built around the actual class problems law students work through each week — starting with patent law. PlanningJudiciary
01The Lab's research partnership with federal courts and the Delaware Court of Chancery.
Judiciary — Teaching the Bench
Working with the federal judiciary on the practical use of AI tools — through training, research, chambers-facing tools, and structured feedback. ActiveTraining
01Training materials for legal-education audiences — and the cross-Penn version of the same package.
Training Materials
Produce a complete AI training package for legal-education audiences — and pitch a cross-Penn version with collaborators. ActiveNewsletter
01The pipeline behind the Lab's monthly AI Updates newsletter.
Newsletter Automation
Build the pipeline that produces the Project's monthly AI newsletter — automated collection, editorial workflow, Substack distribution. ActiveShipped Artifacts
01Lab work already in the world — public-facing artifacts you can read, listen to, and use.