AI Resources

Most people try an AI tool once, get a mediocre answer, and conclude it's not that useful. The difference between a mediocre answer and a genuinely helpful one usually comes down to how you ask. Here's what I've learned works.

Be Specific About What You Want

Don't just say "write me a memo." Say "write a two-page memo to the faculty curriculum committee recommending we add a course on AI regulation, in a professional but collegial tone." The more you specify — format, length, audience, tone — the better the output. Vague prompts get vague results.

Give It Context

AI tools work dramatically better when you give them something to work with. Paste in the document you want summarized. Copy in the email thread you need to respond to. Describe the situation in enough detail that a smart colleague could help you. Context is the single biggest lever you have.

Iterate — Treat It as a Conversation

The first response is almost never the final product. Push back. Say "make this more concise" or "you missed the point about X" or "rewrite the second paragraph in a more formal tone." These tools respond well to iteration, and the back-and-forth is where the real value emerges.

Ask It to Critique Its Own Work

One of the most underused techniques: after the AI gives you a draft, ask it to identify weaknesses in what it just wrote. "What are the strongest objections to this argument?" or "What did you leave out?" This often surfaces issues you'd catch on your own — but faster.

For a more detailed guide to prompting, the AI Law Lab has put together a comprehensive resource:

AI Law Lab Prompt Engineering Guide

New to Claude Code? Start with the basics on the Getting Started tab. If you've already set it up and want to do more, here are some features worth knowing about.

CLAUDE.md — Persistent Instructions

Drop a file called CLAUDE.md in any project folder and Claude Code reads it at the start of every session. Use it for coding standards, project context, preferred conventions — anything you'd otherwise repeat every time. I use mine to set voice and formatting preferences so I don't have to re-explain them. Documentation →

Custom Skills

Skills are reusable prompts you can install and invoke by name — like /commit or /review-pr. The law faculty skills I've built are examples of this. You can also create your own for any workflow you repeat. Documentation →

MCP — Connecting to External Tools

The Model Context Protocol lets Claude Code connect to external services — Google Drive, Gmail, calendars, databases, Slack, and more. This is how I have Claude draft emails, check my calendar, and pull documents without leaving the conversation. Documentation →

Multiple Environments

Claude Code works in the terminal, VS Code, the desktop app, and the web. Your settings, CLAUDE.md files, and MCP servers carry across all of them. Start a task on your laptop, pick it up from your phone.

Full documentation: code.claude.com/docs

Everything above — ChatGPT, Claude, Harvey — uses a conversational interface. But the same AI models are also available through APIs, which let you build your own tools, automate workflows, and integrate AI into custom applications. You don't need to be a software engineer to find this useful — if you can write a basic script (or ask an AI to write one for you), you can use an API.

Why Use an API?

The conversational tools are great for one-off tasks. But if you find yourself doing the same thing over and over — processing a batch of documents, grading with a rubric, extracting data from a set of files — an API lets you automate it. You write a script once, and it runs the same prompt across hundreds of inputs without you copy-pasting anything.

APIs also give you more control: you can choose the model, adjust parameters like temperature (how creative vs. deterministic the output is), and build multi-step workflows where the output of one call feeds into the next.

Anthropic (Claude) API

Anthropic's API gives you direct access to the Claude models — the same ones powering Claude Code and the Claude chat interface, but programmatically. Strong at writing, analysis, long documents, and coding tasks.

• Documentation
• Getting started
• Pricing — pay per use; starts at a few dollars for significant usage

OpenAI API

OpenAI's API gives you access to the GPT models (GPT-4o, o3, etc.) — the same models behind ChatGPT, but with full programmatic control. Broad capabilities across writing, reasoning, and multimodal tasks.

• Documentation
• Quickstart
• Pricing

Other Models

The AI model landscape is broader than just Anthropic and OpenAI. Google's Gemini models are available through their API with similar capabilities. There's also a growing ecosystem of open-source models — Meta's Llama, Mistral, and others — that you can run locally or through hosting providers, sometimes for free. I'm happy to discuss options if you're exploring this space.

Advanced Computing

If you're doing heavy data work — training models, running large-scale analyses, or working with datasets that don't fit on a laptop — the Penn Advanced Research Computing Center (PARCC) provides high-performance computing clusters and storage for faculty research. Niche interest for most, but essential if you need it.

If you're interested in working with APIs and want help getting started, email me. I can point you to examples and walk through the basics.

Use Pro-Tier Models — Always

I want to be very clear about this: do not use free-tier AI tools for any professional work. Free versions of ChatGPT, Claude, and other services may use your inputs as training data, offer weaker models, and lack the privacy controls you need. Always use the paid, pro-tier versions — and typically the most powerful model available.

Just as important: check your privacy settings. Even on paid tiers, most AI tools have settings that control whether your conversations are used for model training. Turn that off. On ChatGPT, it's under Settings → Data Controls. On Claude, it's under Settings → Privacy. Do this before you start using the tool for real work.

Penn Law provides institutional access to Harvey and ChatGPT EDU — these have enterprise agreements with data protections built in (see the ChatGPT EDU FAQ; Harvey details available from me). Use them. If you're using Claude or another tool on your own, make sure you're on a paid plan with training opt-outs enabled.

What's Generally Safe to Share

When you're using a properly configured pro-tier or enterprise tool:

• Published materials and public information
• Your own draft text and work product
• General questions about law, pedagogy, or administration

The key distinction is between information that's already public (or your own work product) and information that belongs to someone else or is institutionally confidential.

Information Security and Privacy

As with any technology, it's worth thinking about what information you're sharing with AI tools — student data, personnel matters, confidential deliberations, and so on. Penn has university-wide guidance on AI use that covers information security and privacy, and the specific terms of service for each tool spell out how your data is handled. I'd encourage you to be familiar with both.

If you have questions about a particular use case, reach out — I'm happy to think through it with you.

Our Institutional Tools

• Harvey — enterprise agreement with Penn Law. Your inputs are not used to train models. Appropriate for most work-related tasks.
• ChatGPT EDU — Penn's institutional agreement with OpenAI includes data protections. Your conversations are not used for model training. See the ChatGPT EDU FAQ for details.
• Claude, Copilot, and other tools — if you're using these independently, make sure you're on a paid plan, using the strongest model available, and have confirmed that your data is not being used for training. Check the privacy settings — they're not always set correctly by default.

AI Hallucinates — Verify Everything That Matters

I said this in the Getting Started tab, and I'll say it again here because it's the single most important thing to understand about these tools: LLMs generate plausible text, not verified truth. They will fabricate case citations, invent statistics, and present made-up facts with complete confidence.

This isn't a minor issue. A lawyer was sanctioned for filing a brief with AI-fabricated case citations. Law review articles have been submitted with invented sources. It happens because the output looks right — and when you're moving fast, it's easy to trust it. Don't. Anything you plan to rely on, share externally, or put your name on should be independently verified.

Attribution

When and how to disclose AI use is still evolving, but the direction is clear: transparency is the right default. If AI contributed meaningfully to a piece of work, say so. For faculty publications, grant applications, and student-facing materials, err on the side of disclosure.

Professor Catherine Struve has put together a thoughtful guide on AI and attribution that's worth reading:

Struve Guide on AI Attribution (Pedagogy Portal)

Bias

AI models reflect the biases present in their training data. This is well-documented and worth keeping in mind — especially in contexts that affect people directly: hiring decisions, admissions-related work, student evaluations, or any process where fairness matters. AI output can be a useful input, but it shouldn't be the sole basis for consequential decisions about people.

Penn Law Exam Policies

AI policies for exams are set by individual faculty and administered through the Registrar's office. The pedagogy portal has current guidance on exam AI policies, including model syllabus language and the different policy tiers available:

Penn Law Pedagogy Resources — Exams

University-Level AI Guidance

Penn has published institutional guidance on AI use:

• Statement on Guidance for the Penn Community on Use of Generative AI — the university-wide framework covering transparency, data privacy, and security
• ChatGPT EDU FAQ — data handling, account access, and usage guidelines for Penn's enterprise ChatGPT

Specific policies vary by context. Research use, classroom use, and administrative use may each have different considerations. When a situation doesn't fit neatly into the guidance above, reach out — I'm happy to think through it.

Curriculum

AI is integrated into the 1L Legal Practice Skills program — students engage AI tools as part of foundational legal training, not as an elective. Faculty across the curriculum have also experimented with AI-integrated assignments, simulations, and new assessment approaches.

Technology Partnerships

We have institutional partnerships with Harvey — one of the leading legal AI platforms, used by major law firms — and ChatGPT EDU, supporting AI use across teaching, research, and administration. Details and access info are on the Getting Started tab.

Faculty Support

Workshops on AI use cases, pedagogy, and tool adoption. A faculty AI toolkit with practical guidance and best practices. Regular communications keeping faculty current on developments. I coordinate all of this — reach out if you want to get involved.

Student Programs

The Madhani Legal Tech Fellowship supports students building legal technology ventures — an established entrepreneurial pathway connecting law students to the legal tech ecosystem.

Faculty Research

Multiple faculty are conducting active research on AI and law — spanning governance, intellectual property, regulatory frameworks, and the structure of legal work.

For teaching-specific AI resources — syllabus language, exam policies, classroom tools, and pedagogy guides — see the companion portal:

Teaching-specific AI guides on the Pedagogy Resources portal

For teaching-focused scholarship on AI and legal education, see the Reading & Research section on the Pedagogy Resources portal.

Below are the sources I follow most closely and recommend to colleagues. This is how I keep up — and honestly, keeping up is half the challenge.