AI Resources

• It reads on its own. A chat tool reads what you paste. An agent reads what it finds — files in a folder you point it at, messages in a connected inbox, web pages it decides to visit. You set the scope; it picks what to look at within that scope.
• It acts; it doesn’t just describe. A chat tool will tell you the command to delete duplicate files. An agent will run the command. A chat tool will draft an email. An agent will send it.
• It plans across many steps. Agents work in a loop: form a plan, take an action, observe the result, revise the plan, take the next action. A single instruction from you might trigger dozens of intermediate steps.
• It uses “tools.” In AI parlance, a tool is anything the agent can call: read a file, run a terminal command, fetch a webpage, send an email, query a calendar. The tools available define what the agent can do. Adding a connector — like Gmail or Google Drive — expands the agent’s reach.
• It works between your prompts. The agent may be working for a minute or for ten between your messages. It doesn’t pause to ask permission for every step unless you’ve configured it to.

• Speed and scope. Agents can do in minutes what would take hours of clicking and typing. The flip side is that they can also do damage in minutes.
• Reviewability. Chat outputs are text you can read. Agentic outputs are actions: files changed, messages sent, calendar invites accepted. Reviewing what an agent did is more involved than reviewing what a chatbot wrote.
• Trust setup. With chat, you decide each turn what to share. With an agent, the agent decides what to read within whatever scope you’ve granted. That makes the initial setup — folder, permissions, connectors — far more consequential than what you paste into any single chat.
• Reversibility of errors. Chat errors are wrong answers you can ignore. Agent errors are wrong actions — a deleted file, a misdirected email, an inappropriately scheduled task. Some are easy to undo; some are not.

Chat AI suits drafts, summaries, explanations, brainstorming, and questions where the input fits in a message and the output is text you’ll review.

Agentic AI suits tasks that span many files, require chained steps, or involve making changes rather than describing them — particularly repetitive or well-defined work.

A note on terminology: “Agent,” “assistant,” “copilot,” and “AI tool” are used loosely and inconsistently across products. The distinction that matters isn’t the label — it’s whether the tool can take action on your behalf without each step being explicitly approved. If it can, treat it as agentic, and apply the cautions in the security guide.

Claude Code is Anthropic's AI coding and productivity tool — it works in your terminal, in VS Code, as a desktop app, or in your browser. Despite the name, it's not just for coding. I use it for writing, research, document production, and administrative tasks. It's the tool behind the Claude Code Skills listed on this page and on the pedagogy portal.

You need a paid Claude subscription (Pro, Max, Team, or Enterprise) to use it. A paid personal plan gives you access to the tool, but it does not carry Penn’s data approvals. Penn’s Enterprise Claude includes Claude Code (provisioned for 1Ls; faculty and staff by request through ITS; Standard includes $50/wk API allocation, Premium includes $250/wk) and is approved for Low and Moderate Risk data.

Getting Started

• Overview & installation — install the CLI, VS Code extension, or desktop app
• Quickstart — walk through your first task
• Law faculty skills — my open-source skills for faculty tasks (install instructions in the README)

If you want help getting set up, email me — I'm happy to walk you through it.

The agentic tools above are prebuilt. If you'd rather build your own — automate a repeat task, process a batch of documents, or wire a model into a script — you can call the models directly through an API. You don't need to be a software engineer: if you can write a basic script (or have an AI write one for you), you can use one.

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.

The Penn LLM Gateway

Penn runs a secure LLM Gateway that provides programmatic API access to a range of models from inside Penn's environment — built for research and tool-building. Penn Carey Law is part of the pilot program. It's the Penn-sanctioned path to API access, as opposed to a personal vendor account, which makes it the right starting point for work that touches Penn data or is funded by Penn. Email me to get connected.

Anthropic (Claude) API

If you'd rather go straight to a vendor, 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-5 family of models — the same models behind ChatGPT, but with full programmatic control. Broad capabilities across writing, reasoning, and multimodal tasks.

• Documentation
• Quickstart
• Pricing

Other Models

Anthropic and OpenAI are not the only model providers. 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.

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.

Working directory hygiene

Create a dedicated working folder for AI sessions — not your home directory, not your Desktop. Use a separate folder for each project and limit the agent’s access to that folder. Only put files in there that you’re comfortable with the agent reading — whatever’s in the folder, the agent can and likely will read.

Conservative connectors

Each connector (Gmail, Drive, Calendar, MCP servers) expands what the agent can see and act on. Enable only what you’re actively using. For now, faculty cannot connect external agentic AI tools to the Law School’s O365 — email, calendar, OneDrive, Teams. Faculty experimenting with other connectors should use personal, non-Penn accounts. Email and calendar connectors of any kind deserve special care — they can send messages and accept invites on your behalf.

Guard against prompt injection

Malicious instructions can be hidden in documents, emails, or web pages an agent reads — and the agent will treat them as commands from you. A PDF that instructs the agent to write a favorable evaluation; an email that instructs a Gmail-connected agent to forward messages externally. Be skeptical when an agent’s behavior changes after it reads external content, and keep sensitive actions (send, delete, network calls) gated behind explicit approval.

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 Penn Carey Law AI Project has a comprehensive resource:

From the Project: we build tools for much of this — exam grading, question generation, custom casebooks, a course-bound virtual TA, and more. See what the Project has built →

The Penn Data Risk Classification

Penn classifies data into three tiers — Low Risk (publicly available; no harm if disclosed), Moderate Risk (not generally public; mildly adverse if disclosed), and High Risk (regulated or sensitive; significantly adverse if disclosed). Most legal teaching, scholarship, and administration touches Low and Moderate Risk data. Personnel matters, student PII, confidential committee deliberations, and similar sit at Moderate or High. The full framework is at isc.upenn.edu/security/penn-data-risk-classification.

AI Tools Reviewed for Penn Law Use

This list draws on Penn Law ITS’s AI guidance and Penn ISC’s service page, checked September 3, 2026. Confirm school-specific access with Penn Law ITS:

• PennChat — Penn's secure, University-hosted, chat-based portal for Anthropic's Claude and OpenAI's ChatGPT, free to eligible Penn users. Daily credits allocate model usage; they are not a stated per-user charge. Approved for Low, Moderate, and most High Risk Data (excluding SSNs and credit-card data; avoid identifiable PHI) — the broadest data approval at PCL, alongside Microsoft Copilot Chat. Requires PennNet / AirPennNet or the GlobalProtect VPN. See the PennChat FAQ.
• Microsoft Copilot Chat — free for all PCL faculty, staff, and students via Penn's Microsoft enterprise agreement. Approved for Low, Moderate, and most High Risk Data (excluding SSNs and credit card data) — matching PennChat as the broadest data approval among general-purpose AI tools at PCL. Web-based AI search, content generation, and summarization. See the PCL ITS Copilot Chat Guide.
• Harvey AI — legal-AI platform via Penn Law's enterprise agreement. Approved for Low and Moderate Risk Data only; do not input high-sensitivity data (clinical, HIPAA/PHI, financial account information, SSNs, or credit cards). Available to full-time faculty, staff, and 2L/3L/LLM students (not 1Ls); adjunct faculty on request to Penn Law ITS. LawKey login at app.harvey.ai.
• Legora — legal-AI platform via Penn Law. Approved for Low and Moderate Risk Data only, with the same exclusions as Harvey. Available to faculty, adjunct faculty, staff, and 2L/3L/LLM students; LawKey login at app.us.legora.com. See the PCL ITS Legora Guide.
• ChatGPT (Penn Enterprise / EDU) — approved for Low and Moderate Risk Data only: no HIPAA/PHI, financial account information, SSNs, or credit cards. Available to full-time faculty (via research funds) and staff (via departmental funds) ordered through Penn Law ITS. On the same footing as Claude, faculty can alternatively fund personal Plus or Pro subscriptions with research accounts (carrying standard commercial terms, for Low Risk data only). See the ChatGPT EDU FAQ.
• Claude (Penn Enterprise) — approved for Low and Moderate Risk Data only: no clinical or HIPAA/PHI data, financial account information, SSNs, or credit cards, and contact ITS before using FERPA-protected student data. Includes Claude Chat and Claude Code (provisioned for 1Ls; faculty and staff by request through ITS); Claude Cowork is not currently available (under University review). Faculty (research funds) and staff (departmental funds) licenses are ordered through ITS (itshelp@law.upenn.edu): Standard ($16/month; 112 messages/5h rolling, $50/wk API allocation) or Premium ($50/month; 225 messages/5h rolling, $250/wk API allocation, includes Fable 5). All licenses require a commitment through the fiscal year; Standard licenses can upgrade to Premium during the year. On the same footing as ChatGPT, faculty can alternatively fund personal Pro or Max plans with research accounts (carrying standard commercial terms, for Low Risk data only). See the PCL ITS Claude Guide and ISC’s Anthropic Enterprise FAQ.
• Zoom AI Companion — in-meeting AI for Zoom: live questions, meeting summaries, smart recordings. Available to faculty, staff, and students with a Penn Zoom account. See the PCL ITS Zoom AI Companion Guide.

Penn ISC's central list reviews additional tools beyond those above — Microsoft 365 Copilot (the premium tier embedded in Office apps; requires a paid per-user license), Gemini for Google Workspace, Google NotebookLM, Grammarly, and others — with their own per-tier mappings. Availability for PCL community members varies; the full Penn-wide list is at Penn Generative AI Tools & Resources. Westlaw AI and Lexis+ AI are covered separately under Penn Law's existing legal research subscriptions.

For AI tools beyond those Penn Law ITS or Penn ISC has reviewed, the framework is the same one Penn applies internally: identify the risk tier of any Penn data involved, check the vendor's data-handling terms, and reach out to Penn Law ITS or me with use-case-specific questions.

Quick Guidance for Law School Work

For teaching prep, scholarship drafting, summarizing public legal materials, and most administrative tasks, the PCL ITS-reviewed tools above work well. For sensitive Penn data — student PII, personnel matters, confidential committee deliberations — PennChat and Microsoft Copilot Chat have the broadest approval among the PCL-reviewed tools (Low, Moderate, and most High Risk); Harvey, ChatGPT EDU, Claude (Penn Enterprise), and Zoom AI Companion are reviewed for Low and Moderate Risk only. For SSNs, credit card data, or HIPAA-protected information: don't put it into any AI tool, period.

Personal-Account Use of Other Tools

If you're using Claude, ChatGPT (consumer version, not EDU), or any other AI tool on a personal account rather than through Penn's institutional access, the Penn approvals above don't apply — you're operating under that vendor's terms. For regular work with public or Low Risk material, I recommend a paid tier for its usage limits. Check training and retention settings on any personal plan; paying does not itself establish stronger privacy protections. Personal-account tools should never see Penn's Moderate or High Risk Data. This comes up most often for adjunct faculty, who have no research account and so are likeliest to be working on their own subscription. Student records are FERPA-protected and don’t belong there.

Agentic AI tools — Claude Code, OpenAI Codex, Gemini CLI, Claude Cowork, and the agentic features inside Claude and ChatGPT — introduce risks the data-classification framework above doesn’t fully cover. They read files on their own, take action on your behalf, and can be misdirected by content they read from external sources. The data-classification rules still apply, but the operational practices that protect Penn data look different.

Full treatment is in the dedicated Agentic & Advanced tab and in the standalone security guide:

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:

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 AI Policy Sources

The authoritative sources, with PCL-specific guidance first:

• Penn Law ITS — AI Tools & Guidance — PCL-specific approved tools, with school-specific user guides for Copilot Chat, Zoom AI Companion, ChatGPT, Claude, Legora, and Harvey (Penn Law access only)
• Penn Generative AI Tools & Resources — Penn ISC's central list of approved AI tools and their data-classification mappings
• Penn Data Risk Classification — the underlying framework for what counts as Low, Moderate, and High Risk
• Statement on Guidance for the Penn Community on Use of Generative AI — university-wide guidance on transparency, data privacy, and security
• Microsoft Copilot Chat FAQ — activation and use details for Penn's Copilot deployment
• ChatGPT EDU FAQ — account access and data handling for Penn's ChatGPT deployment

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 and we'll think it through.

The Project runs about a dozen projects — assessment tools, teaching tools, a course-bound virtual TA, work with the judiciary, and the AI Final Exam study that put a frontier model through eleven Penn Carey Law finals. Each has its own page, with scope and current status, on the Project site.

Browse all Project projects →

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.