Penn Carey Law AI Teaching Lab on AI Teaching Lab at Penn Carey Law

Exam Grader

Sat, 09 May 2026 00:00:00 -0400

Exam Grader is the Lab’s calibration-based grading tool for law-school essay exams. The model doesn’t grade in a vacuum — it grades against a calibration set the faculty member has already scored, learning the rubric from worked examples before scoring the rest of the stack.

Course Materials

Fri, 08 May 2026 00:00:00 -0400

Course Materials is the extraction primitive that sits underneath the rest of the Teaching Tools cluster. The job is narrow and load-bearing: take the messy artifacts of a real course — PDFs, slide decks, casebook excerpts, syllabi, lecture transcripts — and turn them into clean, structured text that other tools can consume reliably.

AI Law Lab Bootcamp

Sat, 21 Mar 2026 00:00:00 -0400

A 2-credit, intensive 2-weekend capstone course delivered March 21–22 and 28–29, 2026. Practice-oriented, built around hands-on simulations using real AI legal tools.

Two parallel tracks

Corporate Track — AI-Powered Due Diligence Sprint

Anchored on Hershey’s 2017 acquisition of Amplify Snack Brands. Students worked in buyer and seller teams with deliberately asymmetric information, triaged 500+ contracts using AI tools, negotiated representations and warranties, and presented Red Flag Reports to a mock partner panel.

Best Practices for AI in Legal Education

Fri, 01 Aug 2025 00:00:00 -0400

The Lab’s flagship faculty-facing document. Organizes student and faculty AI use cases by activity type and academic setting; covers AI training pipelines, efficacy assessment, academic standards, ethical considerations, access and equity, and a glossary of terms.

Casebook Builder

Sat, 09 May 2026 00:00:00 -0400

Casebook Builder is the Lab’s tool for turning a faculty member’s case list into a custom course casebook. Give it the cases you want; it fetches the full opinions, edits them down to casebook form — main cases, squibs, contrast cases, comprehension and discussion questions, and explanatory notes — and assembles them into units and a finished book ready for student distribution. It came out of a faculty conversation about the $300–500 commercial casebook problem: AI plus the right tooling should let faculty assemble exactly the casebook their course needs at a fraction of the cost.

Exam Taker

Sat, 09 May 2026 00:00:00 -0400

Exam Taker is the test-subject side of the Lab’s exam work. The pipeline puts a current AI model in the seat of a law student: it answers real Penn Carey Law finals — the same exams enrolled students sit for — and the answers go into the live grading stack to be scored blind, on the curve, by the faculty who wrote them.

AI 1L Orientation

Mon, 01 Sep 2025 00:00:00 -0400

Programming for incoming 1Ls — covering AI capabilities and limits, professional-responsibility considerations, and how AI tools fit into the work of becoming a lawyer.

Run as part of Penn Carey Law’s 1L orientation in September 2025 and (in earlier form) September 2023. Builds on the Toolkit’s AI Tips for 1Ls and 1L Guidance on ChatGPT EDU Use materials.

AI Syllabus Guide

Fri, 01 Aug 2025 00:00:00 -0400

Drop-in syllabus language for faculty across four policy stances — (1) no written assignments, (2) limited AI use, (3) limited AI use with attribution and a written AI-use statement (Professor Cathie Struve’s Fall 2025 seminar version), and (4) complete prohibition. Faculty are expected to copy these blocks, adapt where noted, and adjust to course specifics.

Course-Website Tooling

Sat, 09 May 2026 00:00:00 -0400

Course-Website Tooling is the build layer underneath the Lab’s Training Materials work. It generalizes the Legal Education at Model Velocity microsite — the four-module microsite, the cloned-voice podcast pipeline, the NotebookLM audio overview, the auto-generated PDF summaries — into reusable templates that future training packages and course microsites can deploy without rebuilding from scratch.

Essay Creator

Sat, 09 May 2026 00:00:00 -0400

Essay Creator is the Lab’s productized version of the law-essay-generator skill: a faculty-facing tool for drafting law-school essay exam questions — issue spotters and fact-pattern questions — that meet assessment-science quality standards out of the box.

Legal AI Tool Guide

Tue, 01 Jul 2025 00:00:00 -0400

A categorized overview of the legal AI landscape — seven domain-specific tool families plus the major general-purpose models (ChatGPT, Claude, Gemini). Built for faculty who want to understand what’s out there without having to track every product launch.

Faculty Retreat AI Demos

Tue, 01 Oct 2024 00:00:00 -0400

Live AI demonstrations for Penn Carey Law faculty during the Fall 2024 Faculty Retreat — image generation, class scripting, hypothetical creation, Virtual TA setup, and AI essay grading.

The retreat materials seeded several of the Toolkit’s faculty-facing resources, including Teaching with Generative AI — Demos and the early Faculty Guide to AI Tools.

MCQ Creator

Sat, 09 May 2026 00:00:00 -0400

MCQ Creator is the Lab’s productized version of the law-mcq-generator skill: a faculty-facing tool for drafting multiple-choice exam questions that pass the structural and psychometric quality checks the assessment literature actually expects.

Heron — A Course-Bounded Virtual TA

Thu, 07 May 2026 00:00:00 -0400

Heron is a virtual teaching assistant for a single course — a chatbot students talk to in Slack. Ask it about a case, a doctrine, or the week’s reading, and it answers from that course’s own materials — the assigned readings, slides, and class transcripts — citing the exact page or timestamp so a student can check the source, and saying so plainly when the materials don’t cover the question. It is named for Heron of Alexandria, the first-century engineer of steam toys and automatic doors: a fitting namesake for a course about invention.

AI Tech Talk #1

Wed, 01 Nov 2023 00:00:00 -0400

The Lab’s first major public event: “You know ChatGPT exists… but now what?”

Held November 2023, the Tech Talk framed the practical questions that the Lab has been answering since: where AI helps in legal work, where it fails, what to teach students about it, and how the legal profession should adapt.

Prompt Guide & Scenarios

Thu, 17 Aug 2023 00:00:00 -0400

The Lab’s oldest publication and still in active use. The CRAFTED framework was first written in August 2023 for ChatGPT 3.5 / GPT-4 and CoCounsel; the principles apply across modern general-purpose AI assistants (ChatGPT, Claude) and legal-specific tools.

Class Simulations

Fri, 08 May 2026 00:00:00 -0400

Class Simulations builds AI-driven exercises around the class problems students already work through each week. Instead of generic role-plays, the simulations attach to the specific hypotheticals a course assigns — so the AI counterparty pushes back the way the doctrine actually pushes back, and students get to see their reasoning tested against something that has to follow the same rules they do.

Resource Menu

Fri, 01 Aug 2025 00:00:00 -0400

The Toolkit’s landing page for Penn Carey Law faculty — a single document that links to the four core publications and serves as the Lab’s faculty-facing entry point.

Most of these documents are revised continuously. Check back for new versions.

AI-Assisted Practice Exam Event

Mon, 27 Nov 2023 00:00:00 -0500

A study event for students working through practice exams in Contracts, Torts, Corporations, and Criminal Law — with structured AI-assistance protocols and a post-event reflection on what helped, what got in the way, and what students learned about their own preparation by working alongside AI.

Faculty Discussion Sessions

Fri, 01 Sep 2023 00:00:00 -0400

Recurring smaller-group conversations among Penn Carey Law faculty — about teaching with AI, drafting AI use policies, and what the Lab is learning from its various workstreams. Run since Fall 2023 in different formats: lunches, working-group meetings, and ad-hoc sessions tied to specific Lab outputs.

Faculty AI Resources

Mon, 01 Jan 0001 00:00:00 +0000

1L Guidance on ChatGPT Edu Use

Mon, 01 Sep 2025 00:00:00 -0400

Written for incoming 1Ls. Covers how LLMs work, what they do well, what they fail at, the “human-AI-human sandwich” workflow that keeps the student in the loop, and concrete prompting tips.

AI Tips for 1Ls

Mon, 01 Sep 2025 00:00:00 -0400

Talking points for orientation sessions and 1L AI-introduction events. Designed as a presenter’s guide for in-person delivery rather than independent reading. Pairs with the longer 1L Guidance on ChatGPT Edu Use.

AI Resources at Penn

Mon, 01 Sep 2025 00:00:00 -0400

A directory of AI resources across Penn Carey Law and the broader University of Pennsylvania — tool access points, training programs, academic policies, and the support contacts who handle each. Updated as Penn’s AI offerings expand. The owning units (PCL ITS, Biddle Law Library, Penn ISC, the centers and initiatives below) are authoritative for current eligibility and terms; links go to those pages.

Faculty Guide to AI Tools

Mon, 23 Sep 2024 00:00:00 -0400

A practical onboarding guide for faculty getting started with general-purpose AI tools — how to set up ChatGPT and Claude accounts, which data-privacy settings to check before uploading anything sensitive, and a starter set of research use cases.

Teaching with Generative AI — Demos

Wed, 25 Sep 2024 00:00:00 -0400

The example prompts used in Polk’s Fall 2024 Faculty Retreat session on teaching with generative AI. Each prompt is reproduced as it was given to the model so you can adapt the wording to your own course.

Creating a Virtual TA with Custom GPTs

Sun, 01 Sep 2024 00:00:00 -0400

A walkthrough for faculty who want to build a course-specific virtual teaching assistant using OpenAI’s Custom GPTs. The same conceptual moves apply to Claude Projects (Anthropic) or Gemini Gems (Google), but the specific UI flows differ — adapt the steps below to your platform. The example throughout is the Lab’s IP TA — a study-and-review assistant for Intro to Intellectual Property at Penn Carey Law.

AI Use Policy Templates

Thu, 01 Aug 2024 00:00:00 -0400

Professor Struve’s attribution-and-disclosure model for generative AI in a writing-intensive seminar, with sample AI-use disclosures students can adapt to specific use cases. The framework treats AI as a tool that requires attribution and process transparency.

Accessibility

Sat, 09 May 2026 00:00:00 -0400

The AI Teaching Lab at Penn Carey Law is committed to digital accessibility for the entire Penn Carey Law community and the broader public. This site is built to meet the University of Pennsylvania’s digital accessibility policy and the Web Content Accessibility Guidelines (WCAG) 2.2 Level AA.

Newsletter Automation

Fri, 08 May 2026 00:00:00 -0400

Newsletter Automation is the build side of the Lab’s monthly AI Updates newsletter. The newsletter has been publishing since February 2025; the project here is the pipeline that produces it — automated collection of candidate items through the month, an editorial workflow that surfaces what’s worth including, and Substack as the distribution layer.

Training Materials

Fri, 08 May 2026 00:00:00 -0400

Training Materials produces a complete AI training package for legal-education audiences — modules, exercises, microsites, and the accompanying media — and pitches a cross-Penn version of the same package in collaboration with Bhuvnesh Jain.

Judiciary — Teaching the Bench

Thu, 07 May 2026 00:00:00 -0400

The Lab’s judiciary workstream — the PennLaw-Judiciary AI Testbed — provides federal judges and their chambers with structured AI access, training, and ongoing support, governed by a formal Memorandum of Understanding. The work spans use-case research, chambers-facing tools, and a continuous feedback loop with participating chambers.

Legal Education at Model Velocity

Sun, 19 Apr 2026 00:00:00 -0400

Legal Education at Model Velocity is a shipped artifact — a four-module microsite on what AI’s pace of change means for legal education, paired with a cloned-voice podcast, a 45-minute NotebookLM audio overview, and 14 PDF summaries that distill the modules into briefing-document form.

About the Lab

Mon, 01 Jan 0001 00:00:00 +0000

The Penn Carey Law AI Teaching Lab researches how AI is changing legal education and practice, builds the tools that put those findings to work, and teaches lawyers, law students, judges, and the profession how to use AI well.

Contact

Mon, 01 Jan 0001 00:00:00 +0000

For inquiries, partnerships, or collaboration: email pwagner@law.upenn.edu.

Mailing address

Penn Carey Law AI Teaching Lab University of Pennsylvania Carey Law School 3501 Sansom Street Philadelphia, PA 19104

Code

All public code: github.com/ai-teaching-lab

Join the Lab

Mon, 01 Jan 0001 00:00:00 +0000

The Penn Carey Law AI Teaching Lab hires research assistants and project leads who want to work at the front edge of AI and the law. We research how AI is changing legal education and practice, build the tools that put those findings to work, and teach law students, faculty, judges, and the profession how to use AI well.

License

Mon, 01 Jan 0001 00:00:00 +0000

Website content

The text and design of this website are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). You can copy, share, and adapt our content with attribution.