law essay writing ai

Content Writing AI in Legal Writing: Draft Legal Documents in Minutes

Legal writing, to me, is not just writing sentences; it’s about wielding language as a precise tool to communicate law’s intricacies. Get this: I, too, find legal briefing and drafting similar to a linguistic labyrinth just like you do. Legal jargon can be a lot to take in – but thankfully, AI in legal writing can balance expert knowledge with efficient communication .

I have personally used AI for legal writing under several scenarios, sharing of the use cases below along with the prompts I use:

Legal Research and Citation:

In my experience, I’ve found that AI can swiftly sift through vast legal databases, saving hours that would otherwise be spent manually researching.

Use Case: Ask AI to retrieve recent case law or statutes on a specific legal topic.

Reusable AI Legal Writing Prompt: 

“Please provide an overview of the most recent case law or statutes related to [legal topic], including any notable changes or developments.”

Drafting Legal Documents:

I’ve witnessed the AI’s ability to generate comprehensive drafts, reducing the time it takes to start working on the finer legal details.

Use Case: Ask AI to generate a first draft of a contract or legal document.

“Create a draft of a [type of document], including standard clauses related to [specific details]. Ensure it complies with [relevant laws/regulations].”

Legal Opinion and Analysis:

The AI’s analytical prowess comes into play here, offering insights and highlighting nuances that might be overlooked.

Use Case: You can summarize and analyze a complex legal opinion or document.

Reusable AI Legal Writing Prompt : 

Provide a concise summary and analysis of the key points in the legal opinion/document [title]. Include any implications or nuances that may not be immediately apparent.”

Client Communication:

Clients appreciate prompt responses. AI can help craft well-articulated messages, maintaining professionalism and clarity.

Use Case: Use AI to generate a clear and concise response to a client’s legal query.

“Compose a response to the client’s inquiry about [specific legal issue]. Explain the situation, potential courses of action, and any relevant legal precedents.”

Legal Blogging or Content Creation:

Leveraging AI for content creation has proven to be an effective way to consistently produce high-quality material.

Use Case: You can use AI to generate engaging and informative content on a legal topic for a blog or website.

“Write an article/blog post on [specific legal topic]. Include key legal principles, recent developments, and practical advice for readers.”

Legal Letter Drafting:

AI is adept at crafting professional and assertive letters, maintaining the necessary tone for legal communication.

Use Case: Generate a formal letter to opposing counsel or another party regarding a legal matter.

Reusable AI Legal Writing Prompt:  

“Draft a letter addressing [specific legal matter] to [name of opposing counsel/other party]. Include relevant facts, legal arguments, and any proposed resolutions or actions.”

Legal Summaries for Clients:

Simplifying legal language for clients is crucial, and AI can assist in making legal information more accessible.

Use Case: Summarize the key points of a complex legal document or court decision for a client.

“Provide a clear and concise summary of the [document/court decision] for the client. Focus on explaining the implications and potential next steps in plain language.”

Regulatory Compliance Check:

AI can efficiently cross-reference complex regulations, ensuring businesses stay within legal boundaries.

Use Case: Assess a business practice or policy for compliance with relevant regulations.

“Examine [specific business practice/policy] for compliance with [relevant regulations]. Highlight any potential areas of non-compliance and suggest adjustments or mitigations.”

Legal Training Materials:

AI can contribute to creating engaging training materials, facilitating effective knowledge transfer in legal education.

Use Case: Generate training materials for legal seminars or workshops.

“Develop training materials on [legal topic] for a seminar. Include key legal principles, case studies, and practical examples to enhance participant understanding.”

Legal Marketing Content:

AI can assist in creating persuasive marketing content that resonates with potential clients, showcasing the firm’s strengths.

Use Case: Create compelling content for legal marketing purposes.

Reusable AI in Legal Writing Prompt:  

“Craft a promotional piece on [specific legal service]. Highlight key benefits, success stories, and reasons why clients should choose our legal expertise.”

Should You Use AI in Legal Writing?

Absolutely!  AI for legal writing is a game-changer, but like any tool, it requires thoughtful consideration. Here are some dos and don’ts, drawing from my experience on AI legal writing:

Dos and Don’ts of Using AI in Legal Writing

AI legal writing Reusable Prompt

Do Use AI for Efficient Legal Research:

Do : Use AI to swiftly navigate through extensive legal databases for research.

Example : Recently, a colleague saved hours by employing AI to compile the latest case law on a complex intellectual property matter. The speed of information retrieval was remarkable.

Do Use AI to Get Drafting Assistance:

Do : Employ AI for generating initial drafts of legal documents.

Example : I’ve witnessed smoother workflows when AI is used to outline the framework of contracts, allowing legal professionals to focus on refining nuances rather than starting from scratch.

Do Use AI for Consistent Content Creation:

Do : Utilize AI for creating consistent and high-quality content for legal blogs or marketing materials.

Example : Our firm increased its online presence by regularly publishing insightful blog posts generated with AI assistance. This not only saved time but also maintained a consistent tone across various pieces.

Do Use AI for Client Communication Support:

Do : Use AI to help craft clear and prompt responses to client inquiries.

Example : During a busy period, an AI-generated initial response bought us time to delve deeper into a client’s complex query before providing a comprehensive reply.

Do Use AI for Legal Training and Educational Materials:

Do : Integrate AI in developing educational materials for legal seminars or workshops.

Example : Our training sessions became more engaging when we used AI to compile relevant case studies and legal principles. It allowed us to focus on delivering impactful sessions.

Don’t Trust AI without Verification:

Don’t : Blindly accept AI-generated content without thorough verification, especially in critical legal matters.

Example : We once had a situation where the AI misinterpreted a recent legal update, potentially leading to incorrect advice. It underscored the importance of human oversight.

Don’t Ignore Ethical Considerations:

Don’t : Overlook ethical considerations, especially when dealing with sensitive client information.

Example : We established strict protocols after an inadvertent data exposure incident. Trust in AI should be coupled with a robust commitment to data security.

Don’t Skip Review and Editing:

Don’t : Skip the review and editing phase assuming AI-generated content is flawless.

Example : We learned the hard way that while AI excels in structure, human intuition is crucial for catching subtle errors that algorithms might overlook.

Don’t Provide Unclear Instructions:

Don’t : Provide vague instructions; be specific to get accurate and relevant results.

Example : Requesting a draft without specifying key clauses led to a generic document. AI excels with precision in instructions.

Don’t Underestimate Human Expertise:

Don’t : Replace human expertise entirely; AI is a tool, not a substitute for legal professionals.

Example : Our team found that while AI accelerates processes, nuanced legal arguments and strategic thinking are inherently human strengths.

The Challenges in Legal Writing and AI to the Rescue

Legal writing is the art of expressing legal ideas and arguments in a clear, precise, and formal manner. It spans over legal documents, such as contracts, court briefs, legal opinions, and statutes. The primary aim of legal writing is to convey complex legal concepts accurately and comprehensively to a diverse audience, from clients to judges. 

Now, let’s talk about the challenges in legal writing—common hurdles that every legal professional encounters:

Precision vs. Clarity:

Legal writing requires a delicate balance between precision and clarity. Legal documents require utmost accuracy, but they should also be understandable to a non-legal audience.

I remember a case where an overly technical contract led to misunderstandings between parties. It shows the importance of clarity in legal writing.

Legal Jargon:

The overuse of legal jargon can create confusion rather than clarity.

In a legal brief, excessively used Latin terms may leave the judge bewildered. It highlights the need to communicate legal principles in plain language whenever possible.

Complex Formatting Rules:

Legal writing has strict formatting requirements, especially in court documents, can be daunting.

A minor formatting error in a court filing can lead to unnecessary delays. It underscores how attention to detail is crucial in legal writing.

Detail and Brevity:

Another challenge is to convey comprehensive legal arguments within the constraints of word limits or reader attention spans.

Drafting a succinct yet comprehensive summary of a complex case for a client proved challenging. It taught me the value of concise communication.

Keeping Up with Legal Changes:

You must stay abreast of constantly evolving laws and regulations to ensure legal writing accuracy.

A legal opinion based on outdated statutes may lead to embarrassing correction. It reinforces the need for continuous legal education.

Diverse Audiences:

Another major legal writing challenge is adapting the tone and complexity of legal writing to suit the knowledge level of different audiences, from clients to judges.

Crafting a client advisory may require you to simplify complex legal concepts without oversimplifying. It emphasizes the importance of audience awareness.

A vaguely worded contract can easily lead to a protracted dispute. It underscores the need for meticulous legal drafting to avoid future legal headaches.

The Bottomline on AI in Legal Writing

Legal writing challenges are imperative and it’s crucial for legal professionals to adeptly communicate the law. Fortunately, AI in legal writing solves one of the major legal writing challenges. AI helps in legal drafting and reviewing content for clarity and precision. However, the role of human touch in polishing AI responses is indispensable.

Recommended Reads:

• How to use AI in Medical Writing [Complete Guide]
• How to Use AI to Navigate User Intent and Hit the Bulls’ Eye [Guide]
• Complete Guide to “Fixing” AI Generated Content
• 11 Ways to Use AI To Improve Writing – Level The Field with Native Writers!
• AI Powered Social Media Marketing [Complete Guide 101]

Recent Posts

• Applications of Generative AI in Healthcare – Uses and Challenges
• AI Powered B2B Lead Generation [2024]
• What is Content Automation And Which Tools are Best for It?
• AI Personalized Content: Beginner’s Guide & Prompts
• What is AI as a Service? Definition, Types, Benefits & Trends
• Affiliate Marketing
• Artificial Intelligence
• Content Scaling
• Business Pitch Deck
• Copywriting
• Newsletters
• Product Description
• Social Media
• Songwriting
• Title and Headline
• Writing Ideas
• Call to Action (CTA)
• Email Marketing
• NLP (Natural Language Processing)
• Proposal Writing
• Writer's Block Problem

Email Address

• « AI in Fiction Writing – Tips, Use Cases and Reusable AI Prompts
• AI in Technical Writing – Examples and Reusable Prompts »
• Privacy Policy
• Terms of Use
• Chat with AI
• AI Email Generator
• Social Media Ads Generator
• Blog Idea Generator
• Blog Outline Generator
• Complete Article Generator
• All use cases >
• Bloggers & Vloggers
• Digital Marketing Agency
• Local Stores
• Freelancers
• All industries >
• Affiliate Program
• Comparisons
• System Status

Get in Touch

Meet, Law ChatGPT

The future of writing.

Let AI create content for agreements, documents, letters, legal research and more.

Frequently Asked Questions

Got questions? We have you covered.

What is Law ChatGPT?

How do i use law chatgpt, do i still need to use a lawyer, does a lawyer check the results of the documents, how long does it take to generate a document, latest blogs.

Read our unique blog articles about various data archiving solutions and secrets

Admin | 16 March 2023

Who owns the copyright of ai generated content.

Admin | 22 March 2023

How law chatgpt uses openai to create legal documents online.

Admin | 28 March 2023

6 ways to use law chatgpt for your legal studies.

Admin | 29 March 2023

Embracing ai-driven legal services: northwestern university launches executive course on chatgpt and generative ai.

Admin | 30 March 2023

Law chatgpt example content: history of a legal concept - separation of powers in australia.

Admin | 1 April 2023

Law chatgpt example content - legal terminology explainer - civil law vs common law.

10 Boilerplate Clause Examples and how to generate them with Law ChatGPT

Admin | 6 April 2023

Law chatgpt example content: translate legal text to german challenge.

Admin | 7 April 2023

Maximizing legal success: harnessing the power of law chatgpt to crush the opposition.

Admin | 4 May 2023

5 steps to mastering legal argumentation with ai: how to effectively include a clause in your contract.

Admin | 19 May 2023

Law chatgpt example contents - explain clause from tesla's usd 5 billion syndicated loan agreement, law chatgpt templates.

Our team of lawyers have pre-defined legal templates to generate your law content within seconds.

Just fill in a few details and Law ChatGPT will do they rest.

Termination Letter

A letter to terminate an agreement

Cease and Desist Letter

Send a letter when somebody is infringing your intellectual property

Consumer complaint letter - defective product or service

Write a formal letter addressed to a company in which you express your dissatisfaction with a product or service purchased from the company

Consumer Compliant Letter - company charging for repair under warranty

Are you tired of companies trying to charge you for repairs that should be under warranty? Ask the AI to draft a letter for you disputing the charges.

Consumer Compliant Letter - dispute an invoice

Have you ever received an invoice that you don't think you should pay? Take action now and protect your rights, ask AI to write a professional letter disputing the invoice and asking for a credit note.

Breach Notice Letter

Ask AI to draft a breach notice letter for you. This formal document is sent to a party when they have failed to fulfill their contractual obligations. When drafting a breach notice letter, it's important to include the necessary information to ensure clarity and legal compliance.

Demand Letter

Ask the AI to draft a demand letter to formally request payment or resolution of a dispute.

Write a Formal Letter on any Topic

Ask AI to write you a formal letter on any topic

Clause generator

Instantly create a custom clause for your agreement

Amend a clause

Make changes to an existing clause

Explain a clause

Enter a clause and get an easy to read explanation of it

Create Boilerplate Clauses

This set of boilerplate clauses are designed to provide a solid foundation for any general contract. The clauses are clear, concise, and easily adaptable to various types of agreements, saving you time and effort in drafting contracts.

Clause Negotiation - justification for including clause

Let AI create compelling argument why the counterparty should accept you adding or amending a clause.

Minutes of Shareholders Meeting

Create Shareholders' Meeting minutes in seconds

Shareholders' Agreement

Ask AI to create a draft contract between the shareholders of a company specifying the rights and responsibilities of each shareholder, including voting rights, share transfer restrictions, and dividend policies.

Create company policy document

Let AI create comprehensive company policy documents like: Harassment and Discrimination,Workplace Health and Safety, Data Privacy and Security, Conflict of Interest, Anti-Corruption and Bribery and many more.

Generate Anything

Let AI generate content on any topic, not just legal.

Translate Text

Translate any text from one language to another

Negotiation Strategy

Ask the AI for a negotiation strategy on a particular agreement, situation or conflict.

Research laws

Ask questions about laws in a country or jurisdiction and receive summary report.

Case Law Finder

Find case law that matches facts

Legal Brief Drafting

Draft a killer legal brief with issue, facts and reasoning

Legal Research Writing

Find relevant case law, statutes, regulations, and secondary sources like law review articles, treatises, and other legal documents

Summarize and analyze cases by extracting important details such as the facts, procedural history, issue, holding, legal reasoning, and rule of law. Provide the case name or citation and ask the AI to help you create a case brief.

Legal Analysis

Analyze legal issues by applying relevant legal principles and precedents. Pose hypothetical scenarios or real-life situations and ask the AI to provide a legal analysis.

Legal Citation Helper

Properly cite legal sources according to the citation style you are using (e.g., Bluebook, ALWD, or OSCOLA). Provide the relevant information, and the AI can generate a correctly formatted citation.

Create study aid

create flashcards, outlines, or practice questions to help you study for exams or improve you knowledge. Tip: can be used by teachers to create student content

Legal Terminology Explainer

Understand and define legal terms or concepts. Ask the AI for definitions, explanations, or examples related to specific legal jargon or concepts

Historical Context of a legal topic

Ask the AI for historical / background information or a historical perspective on a specific legal topic, decision, or legislation

Frame Research Question for a Case

Find information about the historical background and legal precedent for a case strategy. The response generated by AI can provide lawyers with valuable insights and information to prepare a strong strategy for their client.

Case Prep - Generate Insights

Ask the AI to generate insights and facts that may be relevant to the case.

Patent finder

The prompt is a reAsk AI to assist in the search for patents similar to your invention.

Draft a US Federal Court Complaint (BETA)

Let AI draft a US Federal Court Complaint. BETA version.

Draft a Claim (BETA)

Let AI draft a court claim. BETA version.

Purchase of Goods Agreement

A simple agreement to buy or sell goods

Create Agreement Outline

Create an outline of the key clauses needed for your contract

One Shot Agreement creator

Create an entire agreement in one go

Non-Disclosure Agreement

Create an NDA fast

Employment Agreeement

An agreement of employment

Power of Attorney

Give authority to somebody to act on your behalf.

Services Agreement

An agreement to buy services

Promissory Note

A loan document

Privacy Policy

A privacy policy for a website

Affiliate Marketing Agreement

An agreement to appoint an affiliate

Website Terms of Use

Let AI create terms of use for your website

Agency Agreement

Let AI create an agency agreement for you

Memorandum of Understanding (MOU)

Guided prompt to craft a Memorandum of Understanding (MOU) between two parties, detailing terms, responsibilities, and other essential clauses.

Seller Owner Finance Agreement

Let AI create agreement where the seller provides financing to the buyer

Follow-Up Email

Create professional email follow up with just few clicks

Company Press Release

Write a company press release with the help of AI

Article Generator

Turn a title and outline text into a fully complete high quality article within seconds

Content Rewriter

Take a piece of content and rewrite it to make it more interesting, creative, and engaging

Paragraph Generator

Generate paragraphs about any topic including a keyword and in a specific tone of voice

Talking Points

Write short, simple and informative points for the subheadings of your article

Pros & Cons

Write the pros and cons of a product, service or website for your blog article

Summarize Text

Summarize any text in a short and easy to understand concise way

Product Name Generator

Create creative product names from examples words

Academic Essay

Create creative academic essays for various subjects just in a second

Creative Stories

Allow AI to generate creative stories for you based on input text

Grammar Checker

Make sure that there are no errors in your content

Summarize for 2nd Grader

Summarize any complex content for a 2nd grader child

Text Extender

Extend your sentences with more description and additional information

Rewrite with Keywords

Rewrite your existing content with including specific keywords

Tone Changer

Change the tone of your writing to match your audience

Use a dictionary to find all details of your word

Newsletter Generator

Generate a newsletter based on the provided information

Law ChatGPT Benefits

Enjoy the full flexibility of the platform with ton of features

Latest AI technology

Law ChatGPT uses the latest AI technology from OpenAI in combiation with custom legal data training.

More than +25 Languages

Generate your agreements, letters, clauses, board minutes and research immediately in more than 25 languages.

2FA Account Protection

Keep your account secure with 2 Factor Account Protection.

Edit Clauses Easily

Create and edit clauses easily within the user interface. Add new AI generated content to your agreement.

Export Text Results in PDF & Word

Export agreements, documents, letters, research and more directly from LawChatGPT to PDF & Word

Generate complex legal research and analysis in seconds

legal research has become more efficient and accurate, allowing lawyers to focus on more strategic and value-added tasks. AI has also made it possible to analyze vast amounts of legal data and identify patterns and trends that would have been impossible to detect manually.

Law ChatGPT Uses combination of custom legal data training and sophisticated Artificial Intelligence Technology

Law Chat GPT can produce high-quality legal documents, such as contracts, letters, legal analysis and custom clauses, in a fraction of the time it would take a human lawyer to do so.

As an AI-powered product, Law Chat GPT utilizes OpenAI's natural language processing (NLP) and machine learning algorithms to help create legal documents online. Law Chat GPT uses a deep learning neural network architecture to generate high-quality text output that is both accurate and natural-sounding.

Our Partners

Be among the many that trust us

Various Subscription Plans

Most competitive prices are guaranteed

• Prepaid Plans
• Monthly Plans
• Yearly Plans

Top up your subscription with more credits or start with Prepaid Plans credits only

Words Included: 10,000

Images Included: 0

Subscribe to our Monthly Subscription Plans and enjoy ton of benefits

Free Access to Law ChatGPT

USD / Month

• OpenAI GPT 3.5 TURBO model
• 2 500 words credit / month
• Response limit 1 500 words
• Access to Standard Templates
• Option to buy top up credit without monthly fee

Low Cost Access to GPT 4

• OpenAI GPT 4 model
• 25 000 words credit / month
• Response limit 4 000 words

Pro Templates & Response Limit

• 100 000 words credit / month
• Access to Pro Templates
• Enough monthly credit for regular users

For Expert Users

$149.00

• 1 M words credit / month
• Training & Support

Subscribe to our Yearly Subscription Plans and enjoy ton of benefits

Save 100 USD compared to monthly pricing

$490.00

• 4000 word limit
• templates and chat feature

Save 40% for Frequent Users

$599.00

• 4 months free compared to monthly pricing
• 100k words / month
• Pro Templates

Save 25% for Teams & Expert Users

$1,299.00

• 3 months free compared to monthly pricing
• 3 team members
• 1 M words / month
• 1-2-1 Support and Onboarding

Contact With Us

Reach out to us for additional information

Cookies and similar technologies are used on our sites to personalise content, provide and improve product features and to analyse traffic on our sites. By clicking Allow, or by clicking any content on our sites, you agree to the use of these cookies and similar technologies.

Learn more about AI-powered text editor for lawyers

Legal ai that helps you daily.

Draftme is an AI companion for lawyers. Illuminate your work with little things that matter

Trusted by global legal teams, now available to you

Craft excellent legal writing with Draftme

Tools designed to make the best of your written work 24/7 ‍

Make impact with your writing

Draftme AI can augment your language and syntax in a magical way.

How it works: write in any language the way you do, then click Improve writing. Easy.

Your ideas and message will remain the same, wrapped into well-shaped compelling phrases.

Generate any document to your specs

Draftme gives you a wide selection of prompts to create any document from scratch.

How it works: select a document, add your details and get a well formatted document in a few seconds.

Export the document as a Microsoft Word file or a PDF, share it with others easily. ‍

Translate and polish your documents

Draftme AI offers fast and precise translations in over 20 languages.

Your text will be translated close to the original preserving all the legally significant details .

If needed, apply a more native speaker-like tone by using the Improve Writing feature.

Instantly turn your document into bilingual

Draftme AI provides you with automatic bilingual translation.

It does all the mechanical work for you, transforming the original document into two columns while translating it automatically.

You will get a neat, formatted MS Word file that you can polish further. ‍

Other features

Our tools are designed to help you make the best of your written work 24/7

Draftme AI is perfect to generate, analyze and synthesize various texts. Create your own assignments tailored to your daily work.

Always feel safe that your contracts have all important clauses in place. Draftme AI scans your document and suggests what is missing.

Easily find the language you need. Generate as many options as you wish to reach the words you like.

Quickly grasp the essence of any document for yourself, your clients or colleagues.

Draftme AI will analyze the regulation to prepare a brief legal alert.  AI will extract the key points from the regulation as well as the main takeways, ready to share with you colleagues and clients.

Easily convert plain language into business or legal. Simplify complex language into conversational for ease of comprehension.

Draftme AI can quickly retrieve the key terms and obligations of the parties. If needed, you can customize the approach to extraction by adding your own points to extract.

Use our best in class dynamic template builder. Easily create any logic with variables, questions and conditions. Automate your MS Word templates fully saving their formatting and style.

How Draftme is different

Draftme has a number of features that differentiate it from other AI tools:

Upload your MS Word documents, work as you always do

A set of ready commands convenient to use

Export in MS Word, PDF or share by link

Folders and file management

Switch between GPT 3.5 and GPT 4 as you like

AI-powered assistance for your legal studies and research.

A smart note-taking and research tool for forward-thinking law students & professionals.

Save hours on your reading, research, and planning.

genei enables you to improve productivity by using a custom AI algorithm to summarise legal articles, analyse judiciary opinions, and find key information within and across cases, instantly.

We read everything so you don't have to.

Instantly summarise any article case, document, or PDF using our of our custom and cutting edge natural language processing models. Our algorithm mimics human understanding to pick out important details and word them concisely.

Find the legislation and analysis that matters to you.

genei's advanced semantic search function identifies important sentences within and across multiple resources. Pose the questions you want answered and get results based on the contents of the documents.

AI-assisted insights to connect the dots in your learning

Extract key people, organisations, places, numbers, and more from a document. Important information that might have otherwise been missed is structured automatically in note format on the page.

Find out how genei can benefit you

“A lifesaver for those last minute moments in the library, where you need to get through work fast."

“genei helped me find key rulings and legislation within long and complex cases much faster than before.”

"A really handy tool for when I was trying to get through a lot of different articles and essays quickly."

• Enroll & Pay
• Prospective Students
• Current Students
• Faculty & Staff

Law professor outlines risks, encourages best practices to use AI for legal, academic writing

LAWRENCE — One of the biggest concerns regarding artificial intelligence is that people will use it as a writing tool, then pass off the results as their own work. But when Andrew Torrance and Bill Tomlinson tried to list AI as a co-author on a law review article, journals didn’t like that either.

Torrance, the Paul E. Wilson Distinguished Professor of Law at KU, and Tomlinson of the University of California-Irvine have been longtime collaborators. Their early work using AI in scholarly writing has developed into several papers. “ChatGPT and Works Scholarly: Best Practices and Legal Pitfalls in Writing with AI,” written with Rebecca Black of the University of California-Irvine, was published in the  SMU Law Review.

“We wrote a bunch of papers using AI and got them accepted. And along the way we learned a lot about what worked and what didn’t when using AI,” Torrance said. “It’s enhanced productivity a lot. Before, one paper a year or so would be good. Now you can do so much more. We edit ourselves to make sure those pitfalls don’t happen. In some cases, we consider AI to be a co-author. That’s one of the things we learned right away, is be explicit. We celebrate that we use it.”

The paper provides guidelines for those curious about using either of the leading AI engines in their academic writing. They largely apply to any kind of writing, but the authors found while AI can be a useful tool, a human touch is still necessary to avoid faulty work. The guidelines include:

• Using standardized approaches.
• Having AI form multiple outlines and drafts.
• Using plagiarism filters.
• Ensuring arguments make sense.
• Avoiding AI "hallucinations," in which the tools simply make things up.
• Watching for repetition, which the models tend to use.

Torrance is also an intellectual property scholar, so violating others’ copyrights would look especially bad, he said. Making sure citations of others’ work are accurate is also vital.

The researchers provide step-by-step guidelines on usage as well as information about the ethics of AI in writing and its place in legal scholarship.

“It gives you a huge head start when using these tools,” Torrance said. “Remember, these are the absolute worst versions of these tools we’ll see in our lifetimes. We’re on the Model T now, but even the Model T is amazing. But you need to be sure you don’t drive it into a ditch.”

Tomlinson and Torrance also noted using AI allows for “late-finding scholarship.” In traditional publishing, if the science or scholarship changed, that information would have to wait for a new edition. Now, as understanding evolves, writing can continuously be updated. That opens the door for publications that can be “dynamically definitive instead of statistically definitive,” Torrance said, while simultaneously making knowledge more accessible.

Torrance, Tomlinson and collaborators Black and Don Patterson of UC-Irvine wrote that, regardless of what one thinks about AI, it can play an incredibly useful role in academic writing and that those who use it properly can have a decided advantage in productivity.

“We hope this paper allows or helps people to shift some of the mentality around AI. I’m sure we haven’t identified all the possible pitfalls,” Torrance said. “Frankly, a lot of these are mistakes you need to avoid, period. I think a lot of the same principles apply between a human writing and using AI. We thought, as a public service, we should put this out there.”

Regardless of how AI evolves, the authors have laid a foundation for how scholars could use the tool in legal and responsible ways. And a piece of advice Torrance offers students in his legal analytics class can apply to all, even if they’re not in the field of law.

“The tagline for the class is, ‘Be the lawyer who masters AI, not the one who is run over by it,’” he said.

Image credit: Adobe Stock.

Read this article from the KU News Service

Generative AI in the Legal Profession

When Open AI released ChatGPT in late 2022, it galvanized the collective imagination—and collective anxiety. Even lawyers wondered how such new AI technologies would change their profession.

March/April 2023

Introducing the march 2023 issue.

The Implications of ChatGPT for Legal Services and Society

Ethical Prompts

Generative Legal Minds

Assisting Knowledge Workers

Samuel Edwards

November 15, 2023

Conversational AI for Legal Writing: Faster, Better, or Both?

AI is already beginning to reshape the legal profession, arguably for the better.With the help of generative AI tools, especially conversational AI, lawyers can hypothetically get more work done and get it done faster. And they might even benefit from an increase in the quality of their finished work.That said, we're still in the early stages of developing AI for lawyers and understanding the context in which it can be used.One of the most common applications of conversational AI for lawyers is in legal writing. If AI is used, does it empirically make legal writing faster? Does it make legal writing better? Is it capable of doing both?Let's explore.

How Is Generative AI Used for Legal Writing?

Generative AI can be used for a wide variety of legal writing tasks, including drafting contracts and client memos. Essentially, a lawyer can input any question they have and receive an answer, or issue a prompt and have the AI generate a section of content for the lawyer to review.Modern generative AI tools can be used for:

•       Research and background information. It's possible to use conversational AI tools as a kind of search engine, producing research results and background information when necessary. Lawyers can use this feature to quickly and easily gather information or understand the context in which their legal writing work will be relevant.
•       Initial drafting. Conversational AI is also useful for initial drafting. If you practice effective prompt engineering, you can feed the AI a highly detailed, specific prompt that should get the tool to generate an original work that meets all your outlined criteria. Moreover, it can hypothetically do this work hundreds of times quicker than the average human writer.
•       Review and feedback. Some conversational AI platforms are also useful for conducting reviews and getting feedback. After a few rounds of revision, lawyers can submit their works in progress to the AI to verify accuracy, check for mistakes, and even gather insights that can be used to make the material better. We don't generally expect that AI tools exceed the abilities of skilled, experienced lawyers, but an extra set of eyes is always valuable.

The Potential for Generative AI in Legal Writing

If used properly and to its fullest potential, the positive impact of generative AI in legal writing could be enormous.The most obvious benefit is that generative AI saves time. It can greatly reduce the number of hours you need to spend researching and produce large sections of legal documents in a matter of minutes. Granted, not all of this research or produced content is going to be perfect, but it doesn't have to be; as long as it's properly reviewed, the time saving benefits are more than enough to justify its use.Of course, in some cases, it's possible for conversational AI to exceed specific human capabilities in terms of quality as well. Quality is a bit subjective and hard to judge, but it's not unreasonable to speculate that at least some of the content produced by these tools it's better than at least some of the content produced by human lawyers.To better answer the question of the “true” potential for generative AI in legal writing, we would need to see more empirical data.Fortunately, this data is rapidly becoming available.

A New Study: Is GPT-4 Faster, Better, or Both?

A recent study by researchers at the University of Minnesota Law School titled Lawyering in the Age of Artificial Intelligence sought to explore the central question of this article: is conversational AI capable of legal writing faster and/or better than human writers?The study followed 60 students from the University of Minnesota Law School. Each student was assigned 4 different legal writing tasks:

•       Drafting a complaint.
•       Drafting a contract.
•       Drafting a section of an employee handbook.
•       Drafting a client memo.

Students were randomly assigned to one of two groups: one of these groups wrote the pieces entirely independently, while the other group used GPT-4 for assistance. Students who used GPT-4 were trained on how to use the program before drafting their works.After the works were completed, researchers blind-graded the results and evaluated the time it took to draft each assignment.Unsurprisingly, students who used GPT-4 were significantly faster than their counterparts. There were “large and consistent increases in speed.” However, access to generative AI “slightly and inconsistently improved the quality of participants’ legal analysis.” In other words, the gains in terms of quality were significantly lower and less consistent.Additionally, there were some identifiable patterns in the role that GPT-4 played in producing the work. GPT-4 was not equally useful across all tasks. Among the tasks for which GPT-4 was useful, it was measurably more useful in improving the quality of work for lower-skilled participants.This is, perhaps, to be expected. Imagine that in terms of quality and experience, lawyers can be rated on a scale of 1 to 100. If GPT-4 is hypothetically rated at a 75, it's going to be much more useful for improving the work quality of lawyers who are currently rated a 40 than it is for improving the work quality of lawyers who are currently rated an 85.It's also interesting to note that AI assistance was able to produce speed improvements with close to universal uniformity. It helped all students somewhat equally, regardless of their baseline speed.One additional result found by the study was that students were generally satisfied with using AI for assistance with legal tasks . Students were able to appropriately assess the strengths of AI and successfully predicted the tasks at which this tool would be best suited.The researchers suggest that this study provides evidence that law schools should thoughtfully consider the possibility of teaching law students how to use AI appropriately. There are also implications for how legal matters are handled and billed.

Major Implications for Generative AI in Legal Writing

So what are the major implications for generative AI in legal writing, in light of these new findings?

•       Conversational AI is not yet superior to the best lawyers. First, it's important for us to understand that conversational AI tools are not yet superior to the best lawyers. As this study indicated, top law school students don't generally see a significant increase in the quality of their work after using AI. The most talented writers in the legal profession need conversational AI tools even less from a quality perspective. However, since AI is still in its infancy, it's possible that this could change in the future as AI becomes more prevalent .
•       Conversational AI is universally capable of expediting tasks. Even at its current state, conversational AI is more or less universally capable of expediting the completion of legal writing tasks. Remember that in this study, students of all levels saw significant improvements in completion time of their respective legal writing assignments. Even if conversational AI hasn't reached its peak in terms of quality, its remarkable speed is more than enough to justify its use.
•       Lawyers like using AI. Another interesting finding here is that lawyers are generally satisfied when using AI to facilitate the production of legal writing. This may have to do with the fact that they spend less time on the writing task, or it may be because of the streamlined, simple usability of the tool, or it might be because the study subjects simply found the technology to be interesting. Whatever the case, we have data to suggest that lawyers genuinely like using AI – and this is likely to improve as AI tools get better.
•       AI isn’t equally adept at all legal writing tasks. It is worth noting that AI isn't equally adept at all legal writing tasks. This should be totally understandable; tasks that require more nuance and context are naturally going to be less suited for broadly trained conversational AI. While we can expect conversational AI to get better at practically every conceivable legal writing task in the future, we can also expect AI to always be better at more general, broad tasks than more specific, complex ones. It's simply a matter of training volume and familiarity.
•       AI is especially valuable to lower-skilled and new lawyers. AI tools are especially valuable to new lawyers and lawyers with lower skills or less experience. Using AI may allow them to close the gap that used to stand between them and their more experienced, more skilled counterparts. Additionally, drafting and practicing with AI may become a vector through which these lawyers can acquire more knowledge and skills.
•       AI is especially valuable to time-restricted lawyers. We know that conversational AI is capable of producing high quality work, but we're even more confident that AI tools are capable of saving you time, regardless of your skill level or what type of work you're producing. This time saving benefit applies regardless of your current legal writing speed as well. Accordingly, lawyers who always feel like they're on a time crunch and lawyers juggling multiple priorities stand to benefit the most from using AI.
•       Schools and institutions need to start adapting to AI in legal writing. With the prevalence and capabilities of AI, it's only natural that schools and institutions start adapting to the use of AI in legal writing. We can't afford to lag behind in this industry, especially when the benefits of using this technology are so great.
•       The best approach is good lawyers working with AI. As you might have suspected, we now have empirical evidence that the best possible approach is using skilled, experienced lawyers in combination with AI. This way, you get access to the best of both worlds: the speed and efficiency of conversational AI with the expertise, nuance, and creativity of a human mind. There may eventually come a time when all the features of conversational AI exceed even the best humans in the field, but such advancements would be years, if not decades away.

Are you interested in learning more about how AI can be used to improve your legal writing?Or are you ready to build and adopt a legal writing AI tool in your law firm?We can help. Contact us for a free consultation today!

Chief Marketing Officer

Samuel Edwards is CMO of Law.co and its associated agency. Since 2012, Sam has worked with some of the largest law firms around the globe. Today, Sam works directly with high-end law clients across all verticals to maximize operational efficiency and ROI through artificial intelligence. Connect with Sam on Linkedin.

Recent Posts

The Ultimate Guide to Keyboard Shortcuts for Legal Symbols

April 17, 2024

Legal AI Prompts: How to Ask Your AI Questions Properly

April 11, 2024

How Legal AI Increases Productivity for Real Estate Lawyers

April 10, 2024

The Best Lawyer Channels on YouTube (and How to Start Your Own)

March 5, 2024

The How and Why of Preventing AI Hallucinations for Lawyers

February 21, 2024

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.

Stay In The Know.

Contact information.

1425 Broadway Suite 22689 Seattle, WA 98112

© 2023 Nead, LLC Law.co is NOT a law firm. The information on this site does not constitute attorney-client privilege or imply an attorney-client relationship. Furthermore, This website is not intended to replace the professional legal advice of a licensed attorney. Our services and products are subject to our Privacy Policy and Terms and Conditions.

Democratizing Legal AI

Georgetown Law

Ai & the law… & what it means for legal education & lawyers.

January 2, 2024

An AI image generator shows what it could look like if law school classes were taught by robots.

From ChatGPT to algorithms that ace the LSAT, artificial intelligence (AI) is roiling the legal world like perhaps no technology ever has – and this is just the beginning. Georgetown Law students, faculty and alumni are on the frontlines of efforts to come to grips with the baffling range of potential benefits as well as dangers raised by this new era.

“The launch of ChatGPT in November of 2022 was a moment as big as the introduction of the World Wide Web in the 1990s,” says Ed Walters , a Georgetown Law adjunct professor who has long taught a class on the “Law of Robots.” Just as browsers and the Web made the Internet accessible to ordinary people who didn’t necessarily know much about computers, he says, ChatGPT, a “chatbot” tool, brought AI to the mainstream. “It was the first time regular people could see artificial intelligence and relate to it in a way that they understood,” says Walters. Now the algorithmic floodgates have been flung wide open, leaving corporations, governments and practically every kind of institution scrambling to figure out how to adapt to the incoming tidal wave of AI.

AI ENTERS THE ACADEMY

Law schools are no exception. Last March, researchers showed that GPT-4, an upgraded version of the model that runs ChatGPT, could outperform most humans on the Uniform Bar Examination, sending a shiver through the ranks of administrators and educators tasked with evaluating students. In an effort to keep students from outsourcing their application essays or research papers to algorithms, some institutions such as the UC Berkeley School of Law have banned the use of generative AI models in exams and assignments.

Professor Wilf-Townsend

At Georgetown Law, “we considered a complete ban but so far, have decided that was too broad an approach,” says Professor Daniel Wilf-Townsend , who chairs a committee tasked with, essentially, figuring out how the school should deal with AI. “If you can do a Google search while working on an assignment, then why not be able to do a search on Microsoft Bing, even though it also uses ChatGPT? We want there to be a sense that generative AI resources, especially as they get better, can be used by students in contexts where they’re already allowed to use whatever resources they find ready to hand. But that doesn’t mean that it’s no holds barred when it comes to exams, or plagiarism.”

There’s certainly no shortage of interest in the subject: Georgetown Law currently offers at least 17 courses addressing different aspects of AI. Professor Paul Ohm , whose undergraduate degree is in computer science, is teaching two of them. At present, the Law Center is leaving it up to individual professors to set their own policies on whether and how students may use AI, while maintaining existing rules about plagiarism and exams. Some instructors are forbidding their first-year students from using AI, figuring 1Ls need to learn the basics so that they will at least be able to tell if an AI-abetted paper is up to scratch.

Professor DeLaurentis

Others are tentatively allowing some use of the technology. Wilf-Townsend plans to add at least one exercise to his upcoming seminar, “AI & the Law: Principles and Problems,” in which students will use language models to respond to reading materials. And Professor Frances DeLaurentis , director of the Georgetown Law Writing Center , is launching an upper-level class in which students will experiment with using AI as a writing aid – playing with different prompts, taking turns writing and editing with the algorithms. “It can be really helpful for brainstorming topics, and with writing that first draft, especially for students whose first language isn’t English,” she says. “I think the future is hybrid work produced by humans working with gen-AI.”

Alonzo Barber, L’06, who heads Microsoft’s U.S. Enterprise Commercial team, is already there. He had no teaching experience when he agreed last fall to lead a one-week course on “Legal Skills in an AI-Powered World” as one of this year’s Week One experiential electives, so he turned to ChatGPT for help. “I was like, this is my first time doing this adjunct thing. I don’t know what a curriculum should look like. So I type into ChatGPT, ‘Draft me a course description about the legal implications of AI and the law.’ It spit out three paragraphs and I was like, ‘This is pretty good!’” He reworked and refined that outline, of course, but says having that first draft done for him saved him hours of work.

Some students may well use the technology to cheat, but at this point stopping them is difficult. Tools that claim to be able to spot AI-generated text are unreliable, says Wilf-Townsend. And in any case, students have always cheated; in a way, AI might even help level the playing field. “AI puts kids who don’t have an Uncle Alito to call for help with their take-home exam on an equal footing with those who do,” says DeLaurentis.

AI JOINS A LAW FIRM

Beyond academia, Barber believes it’s crucial for legal professionals to not only learn how to use AI tools, but to understand them – how they are built, their strengths, their weaknesses and the ways in which they can fail. Practically every lawyer in America has by now shuddered at the story of the ill-advised attorneys who had ChatGPT write a legal brief that they submitted to a New York federal court – only to find that the brief was filled with nonexistent case citations the bot had simply made up.

AI systems of all types are often plagued with more subtle shortcomings. Many AI-powered face recognition systems, for instance, are more prone to misidentify people of color than they are white people. That’s often because the data sets those systems were trained on included far more white faces. That imbalance makes those systems questionable tools for helping to make decisions about who to arrest in or convict of a crime. Many other AI systems are similarly biased as a result of flaws in the data they were trained on.

“You really want to think about those things, because our profession touches pretty much every corner of society,” says Barber – from criminal justice to legal issues in bank lending and employment. “These technologies will be implemented in all those areas, which makes it important that we as a legal community understand them.”

For some lawyers, the task is to not only understand the algorithms but to defend them in court. Bennett Borden, L’04, chief data scientist at DLA Piper, is part of a team of lawyers and data scientists that helps the firm counsel most of the biggest generative AI companies. These unprecedented technologies are raising unprecedented legal questions. For example, generative AI companies have been sued by individuals who claim platforms produced defamatory statements about them. “These cases are really quite novel,” says Borden. “They raise fundamental questions, like ‘Can you even be defamed by a computer?’”

FRIEND OR FOE?

An AI image generator shows what it might look like if dogs could practice law.

On the other hand, such technology could also help ordinary people use the law to their advantage. Bots can make it easier than ever to, say, fight an unfair eviction notice or contest a firing. “Generative AI should have an amazing democratizing and leveling effect on the practice of law and the judicial system,” says Borden. “It will make the creation of legal products and services easier, and therefore less expensive. So people who previously could not afford to bring a case are going to be able to do that more. And it should boost the capacity of civil rights organizations and pro bono groups to help more people.”

One of the biggest potential upsides to adding AI in to legal practice is that it could supercharge lawyers’ productivity. Algorithms can learn a company’s style and draft bespoke contracts in seconds, or summarize lengthy documents in the time it takes a human attorney to post a vacation shot on Instagram. Big firms are already integrating generative AI models into their practice – for example, London-based Allen & Overy has partnered with a startup on “Harvey,” a chatbot tool its staff can use to help with routine tasks like drafting memos and contracts.

General purpose models like ChatGPT aren’t (yet) reliable enough for most kinds of legal work, but there are plenty of businesses offering AI tools specifically designed for legal professionals. In addition to his teaching at Georgetown, Ed Walters is an executive at one of those companies, vLex. Unlike models trained on the random cacophony of the whole Internet, his company’s VincentAI tool is trained on a database of some one billion legal documents. “You’re not getting answers from trolls on Reddit or comments on YouTube,” says Walters. Instead, he explains, users type in a natural language query and the tool provides an answer with links to relevant cases. “It’s like asking a junior lawyer or paralegal to read all the relevant cases, treatises and statutes and produce a memo. You still need a lawyer to then go and read those cases and decide if that’s the best way to argue. But research that might have taken a week, you can now start while you’re on the phone with a client, and have the answer by the end of the call.”

But if systems like VincentAI work as well as advertised, will companies even need those junior lawyers and paralegals any more? And if first-year associates don’t get to learn under the tutelage of more experienced lawyers, how will they get the training they need to move up the career ladder? In short: Will lawyers lose their jobs to robots?

It’s a concern shared by many, and not just those in the legal field. (Freelance writers, for instance!) Walters, at least, isn’t one of them. “Everyone was afraid e-discovery would put junior lawyers out of work,” he said. “But there are more lawyers than ever now. And they’re happier, because they’re no longer stuck in warehouses reviewing boxes of documents.”

THE JURY IS STILL OUT

One thing is for sure: given all the ethical, social and legal perils AI presents, governments are going to have to get serious about regulating the technology. Miriam Vogel, L’01, President and CEO of the nonprofit EqualAI, sits on a committee that advises the Biden Administration on AI policy. She points out that existing laws do already provide some guardrails on how the technology is used. Race-based employment discrimination is illegal whether it’s perpetrated by a hiring manager or an algorithm, for instance. But AI raises all kinds of new issues that will require new rules.

Legislators are starting to tackle that challenge. Several states have passed laws forbidding law enforcement from using face recognition, and California requires companies to let customers know if they are talking to a chatbot. The European Union is expected to soon enact a sweeping package of rules governing how AI is used. “We can expect much more regulation in the EU, and that will impact anyone doing business there,” says Vogel. And in late October, President Biden issued an expansive executive order that obliges major AI companies to share information on the potential risks of their products with the government and directs federal agencies to set up safeguards around the technology.

It’s a start. But the government, like the legal world, and for that matter pretty much all of us, is still trying to catch up with a technology that is getting better and more powerful all the time.

“We’re at the toddler stage of generative AI,” says Borden. “It’s like when your two-year-old takes his first steps. It’s amazing. But he’s still not very good at walking, compared to an Olympic runner. When these systems start to run, and jump, and fly – that idea fills me with excitement and optimism, but it’s also where things get really scary.”

This article is the cover feature in the Fall 2023 issue of Georgetown Law Magazine . 

Its author, Vince Beiser , is a journalist based in Vancouver, Canada. His work has appeared in Wired, The Atlantic, Harper’s, The Guardian and elsewhere. He is the author of the books “The World in a Grain: The Story of Sand and How It Transformed Civilization” and the forthcoming “Power Metal.”

Writing for & Publishing in Law Reviews

• General: Texts & Advice
• Follow New Developments
• Mine Others' Ideas
• Shape Your Topic
• Search for Published Articles
• Search for Books & Book Chapters
• Search for Working Papers, Upcoming Symposia

Introduction

What is ai, academic integrity, citing generative ai, more on ai in law.

• Type of Journal
• Measuring Quality
• Submitting Papers
• Guide Authors

Artificial Intelligence (AI) is having a transformative impact in almost every industry, including law. However, with the rise of ChatGPT and other AI-based technologies, there are growing concerns about how such tools can be used by some people in unethical ways. This section offers resources to help you distinguish between permissible and impermissible uses of AI in legal writing.

A Primer on Using Artificial Intelligence in the Legal Profession

A helpful article that provides an overview of what AI is and its use in the legal profession.

How ChatGPT Works: The Model Behind the Bot

A brief introduction to the machine learning models that power ChatGPT

Other Library Guides:

• Artificial Intelligence - University of Washington School of Law, Gallagher Law Library
• AI in the Legal Field: Introduction to ChatGPT  - Loyola University School of Law Library
• ChatGPT Resources  - Northwestern University Law School, Pritzker Legal Research Center 

Community Standards & Student Conduct

The use of ChatGPT and other generative AI tools is not expressly prohibited by any one UW policy. However, the use of these technologies may violate certain academic standards.

Law School Honor Code

Use of AI technologies may violate the Law School's academic policies regarding plagiarism. Section 2-101 defines “plagiarism" as "the submission or presentation of someone else's words, composition, research, or expressed ideas, whether published or unpublished, without attribution." Plagiarism includes, but is not limited to:

• The use, by paraphrase or direct quotation, of the published or unpublished work of another person without full and clear acknowledgment; or
• The unacknowledged use of materials prepared by another person or acquired from an entity engaging in the selling of term papers or other academic materials.

The AI Writing Assistant Handbook for Law

How You Should - and Shouldn't Use ChatGPT as a Student

How to Write an Essay with ChatGPT

The Perfect Union? ChatGPT and Legal Writing

Need a break from writing? Here are some other ways that people are using AI .

At this time, there is little consensus on whether AI should be cited as a source of information or treated as a co-author. Nor are there clear rules on how to cite AI in the citation style set forth by  The Bluebook . Law reviews and law journals have varying approaches to the use of AI and AI authorship. At the very least, many journals require some acknowledgment or disclosure regarding the author's use of AI. Carefully review the submission guidelines for each journal or reach out to their editorial staff for clarification.

The upcoming 22nd edition of The Bluebook (likely to be published in 2025), will likely have helpful guidance. Until then, this is our best guess for how a Bluebook citation to a generative AI response should look, with the full citations below:

Full citations:

Microsoft , Response to: "What Is the Official Name of BingChat?”,  BingChat (Jan. 19, 2024, 2:21 PM), https://www.bing.com/ (accessed through the Bing website by selecting "BingChat").

RELX, Response to: "What Is the Official Name of Lexis+AI?", Lexis+AI (Jan. 19, 2024, 2:23 PM), https://plusai.lexis.com/lexisplusai/ (select "ask a legal question").

OpenAI , Response to: "What Is the Official Name of ChatGPT?", ChatGPT , (Jan. 19, 2024, 2:24 PM), https://chat.openai.com/  (enter query into "Message ChatGPT" box).

AI and the Bluebook: Why ChatGPT Falls Short of Traditional Algorithms for Bluebook Legal Citation Formatting

A short article on ChatGPT's inability to properly format citations according to  The Bluebook  style.  

Artificial Intelligence

This takes you to the topic page of Law.com.

The AI Author in Litigation

An article exploring the question of whether AI should be considered an "author" under copyright law.

The Future of Law Firms (and Lawyers) in the Age of Artificial Intelligence

An article describing the impact of AI on the legal profession, the ethical implications raised by the use of AI, and the future of law firms and lawyers in light of the changes brought about by this technology. 

For non-AI writing help, you can check out this research guide on writing resources for legal writers. 

• << Previous: Search for Working Papers, Upcoming Symposia
• Next: Choosing Where to Submit & Publish >>
• Last Updated: Apr 8, 2024 5:40 PM
• URL: https://lib.law.uw.edu/writinglawreview

Enter the URL below into your favorite RSS reader.

“Alexa, Write a Memo”: The Promise and Challenges of AI and Legal Writing

• Citation (BibTeX)

Sorry, something went wrong. Please try again.

If this problem reoccurs, please contact Scholastica Support

Error message:

View more stats

This Article offers an assessment of the present status of AI and legal writing capabilities and also provides a glimpse into the future: what AI is poised to do in the near future and which attorney writing activities seem beyond the reach of AI. As we will see, AI currently can process a natural language description of a legal question or short scenario and return answers and relevant cases. Students still need to read the cases to select and frame legal questions, identify questionable elements, search for cases concerning those elements and analogize them to or distinguish them from the problem scenario, and ultimately, draft the memo. Having done so, however, they can submit the draft memo to an AI program for suggestions of additional issues or cases to cite. For a limited variety of legal memoranda, AI can draft a memo automatically. For certain types of cases, AI can predict an outcome given a textual description of a case’s facts, but it cannot yet provide an explanation or justification. The newest AI can draft a paragraph or two of apparent legal analysis in a sophisticated kind of cutting-and-pasting based on texts in its enormous collection but with no guarantee of legal accuracy.

I. Introduction

As artificial intelligence (AI) capabilities become more and more sophisticated, legal educators and practitioners may have to confront the possibility that in the foreseeable future, AI will be able to write the basic and foundational legal document, the one with which we train our students to first write out legal reasoning, the office memorandum. Even if AI’s ability to write out a full memo is still in the future, [1] at present AI can contribute fruitfully to the memo writing process. Our goal in this Article is to answer these questions: How far can and do AI capabilities go when it comes to legal writing? Can AI do the kind of sorting, analysis, and text generation required for solving legal problems and writing analytical legal documents? What AI skills will new lawyers need in the not-so-distant future in order to be prepared to enter legal practice?

First, however, here is a brief introduction to the field of AI and Law. AI is a subarea of computer science in which researchers develop computational models of behaviors that normally require human intelligence. [2] AI and Law, in particular, focuses on modeling legal reasoning behaviors. [3] Recent developments in AI and in legal text analytics have led to some new tools for legal research, many of which are now familiar to most lawyers and legal educators. Legal text analytics refers to techniques for automatically extracting information from archives of legal documents including case decisions and statutes. [4]

Legal text analytic tools employ machine learning, network diagrams of citations, and question answering. Machine learning (ML) refers to computer programs that use statistical means to induce or “learn” models from data with which they can classify a document as relevant to a claim in e-discovery or even predict an outcome for a new case. [5] Network diagrams graph the relations between objects and can assist in making legal information retrieval smarter. In a citation network , the connected objects may be legal cases or statutory provisions. [6] Question answering (QA) systems search large text collections to locate documents, short phrases, or sentences that directly answer a user’s question. [7] IBM’s Jeopardy-Game-winning Watson program is, perhaps, the most famous example of a QA system. The ROSS program, [8] based on Watson technology, answered legal questions. [9]

We already are seeing AI review contracts and other kinds of transactional “boilerplate” legal documents that vary little from transaction to transaction. Additionally, machine learning is on its way to dominating the discovery process. [10] And we already know that with a few clicks, a computer legal research program can quickly turn up virtually all the relevant law and secondary sources needed in a particular situation—provided the researcher frames the search well—working from vast amounts of data. New developments are inevitable, including AI’s capacity to generate office memoranda, [11] or something that can serve in its place.

Producing an office memorandum, however, is a complex process that involves multiple steps, some of which may already be AI-assisted and some of which may remain forever outside of AI’s range. In Part II, this Article briefly lays out the steps through which a typical legal writer/researcher must go to produce an office memorandum, those same steps to which most legal writing courses introduce students and through which students progress in producing a document. Then, in Part III, the Article briefly introduces some AI techniques for the legal domain and discusses which of these steps AI can currently perform, which steps it will be able to perform in the foreseeable future, and which steps will probably remain in human hands.

This Article lays out a typical office memorandum template that many legal writing teachers use to teach students the form and discusses the possibility of AI writing such a document. It also probes whether AI could write different but equally useful documents.

Finally, in Part IV the Article discusses the teaching challenges that this possibility will pose in the legal writing and analysis classroom. Even if AI may not perform all of the tasks, it will likely be able to participate in writing an office memorandum. If so, what should we be teaching our students? The mere mention of the possibility of AI writing an analytical legal document quickly leads to consternation among law students and legal educators who see AI as threatening an already diminishing job market. That threat indeed might materialize if we do not adapt our pedagogical approaches. Since an entry-level attorney might soon find themself working with AI to produce documents that can be more thorough, accurate, and certainly more quickly produced than those written solely by a human attorney, legal writing courses should prepare students for this kind of AI-lawyer collaboration.

II. How One Gets from a Legal Problem to a Document: A Traditional Approach

In a simple scenario, a client walks in the door and presents an attorney with a problem: someone breached a contract with me; the insurance company won’t pay me; I was injured at the riding stable. The client seeks the attorney’s help in finding a legal solution to their problem and wants to know the chances of success. To analyze the client’s problem, the attorney writes (or assigns someone else to write) an office memorandum. At a granular level, here are ten steps that must be undertaken, from the client walking in the door to the production of the office memorandum. [12] Each step below is accompanied by a simple extended hypothetical to illustrate a concrete example of what occurs in the step.

In Part III, we discuss whether and how current AI capabilities can assist in the process. New software applications for legal practice (“legal apps”) help to address the ten steps but not necessarily in the same order as the manual process. In Part IV, we reorder the steps to address pedagogical goals given AI’s capabilities.

A. Ten Step Process for (Manually) Preparing a Legal Memo

Step 1: interviewing the client and discerning the relevant facts.

Before analyzing the law, the attorney must interview the client and discern what facts in the client’s narrative are legally relevant. [13] The attorney must listen empathetically to the client, who could be distressed, ask meaningful questions to pull out potentially important or clarifying facts, and sort through the story that the client tells to determine the legally relevant facts.

Figure 1 illustrates a hypothetical fact situation that, let us assume, captures the client’s story as told to the attorney.

Client JC, an Evanston, IL, resident, was caring for a friend’s dog when the dog bit MB. Although JC had cared for the dog in the past, on the day that the attack occurred, the friend had dropped off the dog in JC’s backyard without asking JC. JC reluctantly allowed the dog to stay, seeing no choice in the matter, and gave the dog a bowl of water and a treat. JC had a scheduled party while the dog was still in her care and the dog bit a guest, MB, when MB dropped a plate of chicken and the dog went for the chicken. The bite was severe and required multiple stitches. JC comes to the attorney somewhat distressed about the situation and wants to know if she could be liable to MB.

Step 2: Determining the broad legal question and searching for the governing macro-law

Next, the attorney must translate the client’s question (sometimes something as broad as “am I in trouble?”) into a general legal question and begin the research process. Experienced attorneys can usually easily recognize the broad area of law and come up with a general legal question (Is my client liable? Did she break a law? Is he bound by the contract?). Then, before beginning research, the attorney must filter for jurisdiction and area of law, a process that is likely already using technology. Is the legal problem state or federal? If state, which states? Using jurisdictions and keywords in the client’s narrative—for example, landlord/tenant, dog bite, etc.—the attorney can find the governing macro-law.

To continue the analysis of the hypothetical in Figure 1 , JC’s problem is likely governed by Illinois state law. The initial search would be for statutes in Illinois that regulate dog bite cases. The researcher would have to think through all the keywords by which the statute might be found: for example, animal control, injury from animals, dog bite, etc. Nearly any researcher would conduct all of the research online, using one or more of the computer-assisted legal research platforms, such as Lexis or Westlaw. The initial search of Illinois statutes and “dog bite” in JC’s case turns up 510 Illinois Compiled Statutes 5/16 and 510 Illinois Compiled Statutes 5/2.16 (Figures 2 and 3 ).

Animal attacks or injuries. If a dog or other animal, without provocation, attacks, attempts to attack, or injures any person who is peaceably conducting himself or herself in any place where he or she may lawfully be, the owner of such dog or other animal is liable in civil damages to such person for the full amount of the injury proximately caused thereby.

Owner. “Owner” means any person having a right of property in an animal, or who keeps or harbors an animal, or who has it in his care, or acts as its custodian, or who knowingly permits a dog to remain on any premises occupied by him or her . . . .”

Step 3: Pulling out the required elements of the macro rule

Once a governing statute or case rule is found, the attorney must break the rule down into its component parts. What must be shown for the rule to apply? What exceptions exist? How are the rule’s terms defined? The statutes relevant to analyzing the hypothetical in Figure 1 , and the statutes in Figures 2 and 3 , can be broken down into elements as shown in the left column of Table 1 .

Step 4: Applying the client’s facts to the elements

Next, the attorney must apply the client’s facts to each of the law’s required elements, definitions, exceptions, etc. Only then can the attorney see if that law indeed applies and speculate as to the outcome in the client’s case. The attorney must also perceive what parts of the law are ambiguous in the client’s scenario and will require further research. The right column of Table 1 shows the initial results of applying the client’s facts to the elements of 510 Illinois Compiled Statutes 5/16 and 5/2.16.

Step 5: Identifying any questionable elements

Once the facts are applied to the rule’s elements, the attorney can discern what needs further research. For example, elements viii through xii in Table 1 are questionable: it could be ambiguous as to what harboring a dog means, what having a dog in one’s care means, or what acting as a custodian means. It is also possible that JC would not be considered an owner under the statute because she did not knowingly permit the dog to be at her house, although she did knowingly permit it to remain.

Step 6: Searching case law for clarity on questionable elements and sorting through cases for relevance and applicability to the client’s problem

Next, the attorney conducts a search of cases within the jurisdiction in which courts have further defined or at least provided guidelines for the questionable elements. If no cases within the jurisdiction appear to deal with a questionable element, the attorney might look to persuasive authority from other jurisdictions.

With respect to the questionable items in Table 1 (elements viii through xii), the attorney would conduct a search through Illinois case law to see how Illinois courts define “owner” under the statute, focusing particularly on whether it matters if a person knowingly accepts responsibility for the animal. A Westlaw search (on May 23, 2022) of “‘510 ILCS 5/1’ AND owner” turns up forty-six cases and blurbs saying anyone who harbors or cares for a dog and who places himself in the position of an owner taking on owner-like responsibilities is liable even if not the legal owner. Not all forty-six are relevant, and the attorney would have to select the “best” cases. The cases would need to be filtered for similar facts—non-owner caring for dog that injures someone. Other factors, such as level of the reviewing court and date, also go to relevance. The attorney must at least skim through all forty-six of the cases to see if the facts are analogous and to decide if the court’s analysis would apply to JC’s situation in order to narrow the search to the five [14] relevant (“best”) cases.

Step 7: Synthesizing a rule from the relevant cases

This step entails several complex sub-steps: organizing the cases as to outcome; carefully analyzing the reasoning in each case to determine why the court held as it did, that is determining what principles or rules the courts used in reaching their decisions, some of which may not be explicitly stated in the cases; and then synthesizing the various rules from the cases to speculate as to what rule a court in the jurisdiction would apply in the client’s case. In some instances, binding precedent may not be on point or may be absent. In that case, an attorney/researcher would look for similar cases in other jurisdictions in order to think through a likely outcome.

The relevant cases would be organized by whether the court found that the animal caretaker was the owner and why. For example, the top row of Table 2 illustrates one positive and one negative case.

The line between yes and no, that is between whether a caretaker is an “owner” and thus liable or not, seems to be the following: whether the caretaker voluntarily assumed a significant level of care and control of an animal, similar to the level of care and control a legal owner assumes, such as feeding, providing water, and letting outside. Smaller actions, like occasionally providing food or water, if not required for the care of the animal, do not rise to the level of care required for liability. This statement would be the synthesized rule.

Step 8: Analogizing and distinguishing searched cases

Next, the searched cases would be analogized to or distinguished from the current case by comparing the client’s facts to the facts in the cases. The bottom row of Table 2 illustrates distinguishing the positive case and analogizing the negative one.

Step 9: Predicting the outcome

An attorney would then assess the results from the steps listed above and speculate as to what would happen should a court consider the client’s case. A good attorney, however, would do more than compare the cases and outcomes. He or she would research and think through the purpose of the law in question. What outcome were the lawmakers seeking and how would a likely outcome in the client’s case fit into the law’s purpose?

In the extended example, an attorney would think through how a court would apply the synthesized rule in Step 7: A person is an owner under the statute when that person voluntarily assumes a significant level of care and control of an animal, similar to the level of care a legal owner assumes, such as feeding, providing water, and letting outside. It seems a likely outcome that JC would not be considered an owner when the attack occurred because her friend dropped off the dog without JC’s knowledge and JC had not voluntarily assumed owner-like responsibilities for the dog. The attorney would also have to consider and weigh possible counter-arguments—what actions did JC take, like allowing the dog to remain, albeit reluctantly, and giving the dog water and a treat—that could constitute owner-like care and control. Finally, a thorough attorney would take into account the statute’s purpose—to compel people who have responsibility for an animal, even if not legal owners, to control the animal so that the animal does not injure someone.

Step 10: Writing the office memorandum

All of the steps listed above would have to be translated into some kind of document that could be used by another attorney to advise the client. Typically, this document is an office memorandum. See Appendix A for a legal memo, drafted by a human attorney, that addresses the various points made above.

III. How AI Would Help to Prepare a Legal Memo

Having seen the steps that law students would be taught in preparing a legal memo, let’s now examine how AI could be involved in each steps. For purposes of exposition, we will take the steps in the order presented above and examine the extent to which AI approaches can perform them. As we will see, some steps are currently beyond AI capabilities, and some will always be so, but others are matters of research in AI and Law and may be possible in the foreseeable future.

Sometimes the AI approaches address the steps or parts of steps in a different order; sometimes they skip ahead or combine parts of different steps. In Part IV, we will summarize how law students currently could apply AI tools to address the memo writing task and how students might be taught the still relevant lessons of the traditional approach. As illustrated there, the steps may be reordered depending on which parts are automated and which are still manual.

AI approach to Step 1: Interviewing client, discerning relevant facts

A legal app probably could not engage in a freeform aural conversation with JC to obtain the facts (Traditional Step 1). Along these lines, researchers in AI have built user interfaces or chatbots that are able to ask clients for details about their facts. [15] The medium might be audio, but more likely it would combine menus and short text fill-ins in response to written questions. A program probably cannot yet interpret a client’s audio rendition of their problem scenario due to its length and the tendency of humans to speak in sentence fragments and sometimes ungrammatically or emotionally. [16]

Although empathy should be part of the lawyering process, AI systems listening empathetically may be unlikely for some time. Thus far, AI systems are able to detect positive and negative sentiments in text and in the kinds of voice communications involved in customer service applications. They are still a long way from distinguishing emotions such as anxiety or distress, drawing indirect inferences, or reacting to emotions by responding empathetically. [17]

A legal expert system is a kind of computer application that can “provide advice specific to a given scenario” based on a human “experts’ knowledge captured in a sophisticated and often complex logic or rule base.” [18] If one were available, it would drive the questioning in Traditional Step 1 using a set of human-authored rules defining the relevant claims and their requirements. [19]

Such an expert systems app would be restricted to a small list of particular types of legal claims for which humans had created a list of rules. Assuming that someone has created an app for dogbites under Illinois law, Figure 4 shows a sample set of questions driven by rules derived from the language of the statute, 510 Illinois Compiled Statutes 5/16 and 5/2.16. Given the limitations of current natural language processing techniques, the human expert would have to produce these rules manually because it is not yet possible for a program to analyze the texts of such statutes and generate rules automatically. [20]

• Was someone attacked by a dog or other animal?
• Was the dog provoked in any way?
• Did the attack occur in a place where the victim had a legal right to be?
• Was the victim of the attack conducting themself in a peaceable way?
• Who owns the dog?
• Who owns the premises where the attack occurred?
• At the time of the attack: a) Who was keeping or harboring the dog? b) In whose care was the dog? c) Who was acting as the custodian of the dog? d) Who permitted the dog to remain on the premises occupied by him or her? e) Did the person knowingly permit the dog to remain on such premises?

The expert systems app would ask questions in order to narrow down which of the claims is relevant. The order of questions, however, might be flexibly determined by the order in which the client provides inputs. Where necessary, the questions would be supplemented with additional, more factually specific questions and menus of possible responses. While users might fill in blanks with names of the victim, dog owner, and so on, the ability of AI programs to interpret free text is still limited by the need for training machine learning with many instances of possible answers. [21]

A system would need a set of expert rules covering an area of law in order to focus on the right questions to ask about facts. Probably no AI program could ask questions of the type appropriate for Traditional Steps 1 and 2 across the broad range of problems with which a practicing attorney regularly deals. Conceivably, however, a system could be an expert on interviewing more generally about types of injuries to various economic, physical, and emotional interests and their causes for purposes of identifying the relevant areas of law and claims or computing damages. [22] For example, it might ask:

Were you the victim of an injury? (Yes / No)

What kind of injury did you experience? (Medical Injury / Property Injury / Pain and Suffering / Emotional Distress / Lost Wages / Other)

Did someone or something cause the injury? (Yes / No)

What kind of person or entity caused the injury? (Person / Corporation / Government Officer / Other)

How did the person or entity cause the injury? (Carelessness / Intentional Act / Defective Product / Other) [23]

Alternatively, a human would need to ask such questions, and having identified potentially relevant claims, could direct the client to an appropriate expert system with expertise in those kinds of claims (if one is available to the attorney) which could then ask claim-related questions to generate a set of facts like the hypothetical of Figure 1 .

Thus, although an AI system cannot interview empathetically or generate relevant questions from a statute, with significant human intervention in creating lists of questions from statutes, AI systems could improve efficiency in client interviews. [24]

AI approach to Step 2: Determining legal question, searching for governing law

Similar considerations arise with respect to determining the applicable jurisdiction and governing law. Presumably, an expert system would ask questions to establish facts on which to determine what subject matter jurisdiction would apply (Traditional Step 2). This would, again, require a set of human-authored rules dealing with at least some of the ins and outs of tort jurisdiction keyed to the type of claim, such as where the injury occurred and where the action that caused the injury occurred. [25]

A key component of Traditional Step 2 is framing the general legal question with which to begin the research process. In the hypothetical, the human searches for statutes governing dogbite cases by submitting keywords such as animal control, injury from animals, and dog bite to Lexis or Westlaw, having selected a library including Illinois statutes.

With AI and natural language processing, framing the general legal question is not entirely necessary to obtain retrieval results. A more direct route is simply to submit the text of Traditional Step 1’s hypothetical ( Figure 1 ) directly to a program such as Westlaw Edge, which supports analyzing natural language descriptions of problems. [26] If we submit the text in Figure 1 and specify the Illinois state library, a Westlaw Edge search (on May 23, 2022) retrieved sixty-eight cases, of which the top-ranked case is Goennenwein by Goennenwein v. Rasof , 695 N.E.2d 541 (1998). This case deals with a “Minor guest who was bitten by property owner’s son’s dog on owner’s premises brought personal injury action against owner.” All of the top-ten cases appeared to be relevant. In addition, selecting “Statutes & Court Rules” leads to the Illinois statute, 510 Illinois Compiled Statutes 5/16 Animal attacks or injuries and 510 Illinois Compiled Statutes 5/2.16 Owner.

Casetext is another program that can process natural language text. [27] It invites users to upload a brief to find relevant cases with CARA A.I. (which we will try later on), but let’s see what Casetext does when we submit into the search box the text of the hypothetical in Figure 1 . On specifying Illinois as the jurisdiction and cutting and pasting the hypothetical into the search box (on May 23, 2022), Casetext retrieved twenty-four cases. Based on the blurbs generated by Casetext, ten of the cases dealt with dog bites but only one blurb flagged the issue of ownership of the dog. On searching within the results for the relevant statutes, three cases referred to the 510 Illinois Compiled Statutes 5/2.16 definition of owner; one referred to 70/2.06 which appears to be a shorter version under Act 70, Humane Care for Animals Act. [28]

While these AI-employing legal information retrieval tools can process natural language descriptions of problems as inputs, one still must read the program’s outputs of cases and statutes to see how they frame the legal question and bear upon it (as is also required for Traditional Steps 3 through 9).

If an attorney does frame a legal question explicitly, however, another AI approach is to submit it to a legal question answering (QA) system. An attorney inputs a question, and the program searches a database of case texts to identify sentences or short texts that appear to directly answer the question. [29] Until its recent shutdown due to a copyright dispute with Thomson Reuters, [30] the ROSS program was the best example of a commercial legal QA system. [31]

As noted in Part I of this Article, ROSS was based on IBM Watson. [32] An attorney could input a question in plain English, and ROSS answered with short passages drawn from cases. [33] For example, prior to ROSS’s closure, we submitted the query, “Is someone who is caring for a friend’s dog liable if the dog bites another person?” ROSS output numerous cases on liability for dog bites. [34] Machine learning (ML) was a key component of legal question answering in ROSS. [35] An ML model learned how to assess the probability that ROSS understood the user’s question, that it is a question it “knew” how to answer, and that a short text extracted from a case, in fact, answered the query. [36] Impressively, six of the top-ten ranked cases dealt with the specific issue of whether someone other than the dog’s owner could be liable and elaborated some conditions relevant to the issue.

Prefacing the first question with "In Illinois, . . . " led ROSS to return cases from that state, four of the top ten of which appeared to discuss the liability of persons other than the dog’s owner. Switching to the Illinois database and specifying Statutes & Regulations, ROSS lists 510 Illinois Compiled Statutes 5: Animal Control Act at rank five, although one must then explore on their own to find the most relevant sub-provisions. Interestingly, submitting a question differently phrased from the first query but with a similar meaning, “If a dog injures a guest while at the premises of a property owner, is the property owner liable for the injury even when the dog belongs to someone else?” yields only one obviously relevant case in the top ten. When one submits the whole text of the hypothetical, ROSS was unable to process it.

While ROSS-like tools provide a quick start to the research, the human user must still select the best cases from the ones that a tool returns on the basis of the extracted short texts and read them to determine the extent to which they answer the user’s question sufficiently to be incorporated in the memorandum. Similarly, if one submits the question “In Illinois, if a dog bites someone, is the caretaker who is not the owner liable?” to Google, it returns the answer in under a second. A lawyer could not rely on that source but would have to circle back and look at the actual statute. Nevertheless, it also provides a quick start.

Thus, AI tools can help students begin to frame a legal question and search for governing law, but the burden remains on the students to evaluate and adapt their results.

AI approach to Step 3: Pulling out macro rule’s elements

It may seem a straightforward task for law students to break down statutory provisions like 510 Illinois Compiled Statutes 5/16 into a list of elements like that in Figure 4 , but it is not something that comes naturally. Students need to be taught why the task is useful and how to perform it. They also need some practice in doing so, but they pick up the skill fairly quickly.

Computers would not pick up the skill so easily, if at all. In general, AI programs cannot yet generate a logical rule summarizing a list of elements and exceptions directly from the text of statutory or regulatory provisions. [37] While a natural language parser like the Stanford Parser [38] has no apparent difficulty in parsing, that is, working out the grammatical structure of, the sentence-long texts of 510 Illinois Compiled Statutes 5/16 or 5/2.16 ( Figure 2 and Figure 3 ), it cannot recognize which parts correspond to elements of the legal rule. Other statutory provisions are much longer, more complex, and more challenging to parse. Statute sentences often contain long lists of items or nested subordinate clauses, making parsing much more difficult. Even automatically segmenting the provision into sentences presents technical challenges. [39]

Once the statutory provision is parsed and segmented, other problems present themselves. One needs to recognize the discourse structure such as defining a term or stating a regulatory rule. If the latter, does the rule impose an obligation or prohibition, or does it provide a permission? Knowledgeable humans recognize these distinctions fairly easily; computer programs must be trained to do so. [40]

The statutory texts pose more difficult questions of semantic interpretation than most texts. For instance, statutory section 5/16 refers to “owner,” a term that has an ordinary meaning, but this is not an ordinary usage of a commonsense term. In fact, it is an indirect and implicit reference to the technical legal term “owner” as defined in statutory section 5/2.16. An astute legal professional would know enough to check which terms such as “animal,” “dog,” “owner,” or “person” are defined in the statute. They all are. The professional would likely note that according to 510 Illinois Compiled Statutes 5/2:

Sec. 2. As used in this Act, unless the context otherwise requires, the terms specified in the Sections following this Section and preceding Section 3 have the meanings ascribed to them in those Sections.

The professional would also note that section 5/2.16 follows section 5/2, which specifies and defines a term (i.e., “owner”), and precedes section 5/16. Thus, the professional would tentatively conclude that “owner” in section 5/16 has the meaning specified in section 5/2.16. Of course, they are left to wonder when “the context otherwise requires” a different meaning. This kind of statutory reasoning about what “owner” means is simply beyond the capacity of current AI systems.

A longtime goal of AI and Law researchers has been to build programs that could automatically summarize the elements specified in a statute and generate logical rules that succinctly capture the statute’s requirements. [41] The researchers try to enable programs to recognize patterns in legislative language that specify requirements. [42] Some work focuses on processing statutory provisions, which, like the Illinois dog bite statutes, comprise multiple sentences, such as a provision from the National Pension Law addressing suspension of pension benefits. [43] Progress has been made in limited domains like building regulations, but the general problem remains unsolved. [44]

An additional complexity is that statutory provisions can be subject to a kind of logical ambiguity due to the fact that, unlike logicians or mathematicians, legislators do not use parentheses to specify the scopes of logical connectors such as “if,” “and,” “or,” and “unless.” [45] They also make extensive use of cross-referencing, either explicitly or implicitly as with the “owner” example above. As a result of this syntactic ambiguity, even fairly simple statutes may exhibit multiple logical interpretations, which litigators are left to discover and exploit as the occasion demands and which create thus far unsolvable problems for AI systems. [46]

Consequently, the system designers of AI legal apps need to employ humans to extract the lists of elements specified by statutes and their logical connections and manually fashion them into rules that computer programs can employ. The rules that power legal expert systems or computational models of legal argument have largely come from human interpretation of the legal texts. [47]

Once lists of elements have been extracted, an AI legal app can suggest them to users as appropriate. For example, Lexis Answers, a relatively recent question answering service that law students may encounter when using Lexis+, suggests claim elements to a user based on the user’s partial input. [48] For instance, if a user types in “breach of contract,” it will suggest questions like “What are the elements of breach of contract?” and “What is the definition of breach of contract?,” among others. Upon selecting the question, “What are the elements of breach of contract?,” it lists the elements and provides links to three cases with such listings. Lexis Answers, however, cannot deal with all types of claims. [49] Upon inputting to Lexis+ the query, “What are the elements of a claim for dogbite?,” Lexis Answers was not activated. Thus, it seems that automatically extracting lists of elements may still be difficult even from cases containing such lists.

AI approach to Step 4: Applying client’s facts to the elements

In general, current AI systems would not understand the description of the hypothetical in Figure 1 well enough to determine which elements in Table 1 are satisfied. This would require more of an ability to understand what a sentence means, that is, what the sentence entails, than AI research has achieved, but not for lack of trying.

There has been a great deal of research in natural language inference and textual entailment. “Natural language inference is the task of determining whether a ‘hypothesis’ is true (entailment), false (contradiction), or undetermined (neutral) given a ‘premise.’” [50] Table 3 illustrates the problem in the context of the dogbite hypothetical.

Each row in the Premise column contains one or two sentences, that is, the premise. The Hypothesis column contains assertions that may or may not be entailed by the corresponding premise. The Relation column specifies whether the hypothesis is entailed by the premise, contradicts the premise, or is neutral with respect to the premise. Items 1, 2, and 3 are straight-forward examples of common sense inferences about the hypotheses given the premise. Modeling this kind of natural language inference has been the focus of AI research. [51]

In item 4, the premise is expanded to two sentences: the factual sentence about JC plus a clause excerpted from the definition of owner in 510 Illinois Compiled Statutes 5/2.16. Similarly, each of items 5 through 7 adds an additional clause from that statutory definition. The hypotheses in each of these four items specifies the dog’s legal owner, by which we intend to indicate that the meaning of “owner” is not the common sense meaning but the technical legal meaning.

These fairly simple modifications take the phenomenon well beyond the current AI research on natural language inference for several reasons. First, the premise involves two sentences, and the second of those involves multiple “OR” clauses. Second, the hypotheses specify the use of a technical legal term, “legal owner,” which definition is specified in the premise. Third, drawing inferences about the term presupposes knowledge of the distinction between common sense terminology/conclusions and legal terminology/conclusions. Let us ignore a fourth complexity— the subtle ambiguity in the meaning of “legal owner.” It may mean “owner as defined by law” but it may also mean “rightful owner.”

The task is similar to taking a bar examination in that one must know the elements of a claim or the requirements of a statutory provision and determine if they are satisfied or not given the facts of the problem. AI and Law researchers developed a system to answer true/false questions from a Japanese bar examination based on statutory texts. [52] Their approach involves matching the question to textually similar provisions of the civil law. In an entailment step, it predicts if it follows logically from the facts in the question that the elements of the provision are satisfied. [53] The hypothetical of Figure 1 , however, appears to be longer and more complex and to involve considerably more common sense knowledge than the true/false exam questions dealt with in that work.

We have been speaking of AI research on understanding natural language text. A more traditional AI approach would involve expert systems. If an expert system were provided with rules from a human expert concerning the elements of legal claims for dogbite and the related kinds of facts, it could ask the client or the attorney about the facts from which the system could infer which elements were satisfied. Here again, the expert system would be limited to those sorts of claims for which someone had created sets of rules. As mentioned, there is still no way for an AI system to automatically infer such rules from the text of statute.

AI approach to Step 5: Identifying any questionable elements

So far, our account of determining which statutory elements are satisfied has omitted the task of determining which of the elements involves terms that are vague or ambiguous. An AI legal app would need to know if the term is vague or ambiguous in order to decide whether the term’s application to the dog bite hypothetical is debatable and subject to argument. Consider, for example, the italicized terms in elements ii and viii through xii in the left column of Table 1 : without provocation, having a right of property in an animal, keeps or harbors, has it in his care, acts as its custodian, and knowingly permits . They are all debatable terms given the particular facts of the dogbite hypothetical. Other facts might make other terms debatable. Even “person” may be debatable in an age of robotic dogwalkers (or “dog” in an age of robotic pets).

Every law student taking an issue-spotting exam needs to determine which legal questions presented in the fact situation are “hard” and which are “easy” to answer, that is, which require considering arguments pro and con and which are not reasonably debatable given the facts. For quite some time, researchers in AI and Law have focused on how to identify the terms in a legal rule whose applicability in a given fact situation is arguable. As early as 1987, a computer program could distinguish “hard” and “easy” questions concerning offer and acceptance in contracts exams but only in manually-prepared representations of case facts. [54]

Today, it is feasible to process the the kinds of textual descriptions of facts that law students must analyze, but text processing is not sufficient. In general, AI has not computationally modeled the ability of lawyers to understand and creatively exploit opportunities for argument presented by specific facts based on the meanings of the statutory terms and particular facts or purposes underlying the regulations. [55] Just as AI and Law has not focused on the distinction between commonsense and technical meanings of statutory terms, it also has not considered whether a term’s meaning is vague, ambiguous, or open-textured as applied in a given set of facts, at least not from scratch. Here, “from scratch” means without some human expert or system designer having already manually specified which of a rule’s terms have been argued about in the past.

Instead, a long line of AI and Law systems have relied on human experts and system designers to manually specify in advance which of a rule’s terms can be or have been argued. [56] The terms serve as an index into a set of past cases in which courts have interpreted a term’s meaning in a given set of facts and decided whether the term applied or not. [57] The system uses those links to find relevant cases and generate arguments by analogy that the same result should apply in a current fact situation.

The ability of an AI system to detect these debatable issues and argue about them in the context of a particular fact situation depends on the availability of a corpus of cases, indexed by those issues which were argued about, and depends on a representation of their facts and those of the new problem. These programs represent the facts of cases not as texts but using certain factual features, such as criterial facts as in GREBE [58] or factors in the “hypo” line of programs (i.e., HYPO, [59] CATO, [60] CABARET, [61] IBP, [62] and VJAP [63] (the Value Judgment-based Argumentative Prediction program)).

A criterial fact is one that a court stated was important in deciding whether the term of a legal rule was satisfied in a particular case. GREBE represents a case as a semantic network with the court’s conclusions about the claim and its elements at or toward the topmost point of the graph and the facts the court deems criterial for its conclusion toward the fringe. [64] Figure 5 illustrates three criterial facts the court in Steinberg v. Petta regarded as important in concluding that the defendant could not have harbored or kept an animal.

The defendant cannot be deemed to have harbored or kept an animal, as those terms are used in the Act, where he: 1) was an absentee landlord, 2) simply allowed the tenants to have a pet on the premises, and 3) did not have the tenants’ dog in his care, custody, or control.

Factors are stereotypical patterns of fact that tend to strengthen a side’s argument concerning a claim or element. Figure 6 illustrates some factors that might be important in determining if a defendant keeps or harbors an animal.

Plaintiff’s argument that defendant “keeps or harbors an animal” is strengthened to the extent that defendant:     F1. exercised some measure of care, custody, or control of the animal.     F2. paid expenses in connection with the animal.     F3. requested the presence of the animal on their premises.     F4. owned an interest in the animal.     F5. was responsible for and had a right to custody or control of the animal.

Plaintiff’s argument that defendant “keeps or harbors an animal” is weakened to the extent that defendant:     F6. did no more than merely permit the presence of the animal on their premises.     F7. was merely a passive owner of premises where animal attack occurred.     F8. exercised minimal care, custody or control of the animal.

The system designers would have determined which terms had been subject to dispute in past cases and represented the case facts manually to enable the systems to make arguments by analogy. As noted, in the hypo line of programs, for example in VJAP, past cases are represented in terms of certain factors associated with the courts’ decisions whether legal terms were satisfied. In the GREBE program, criterial facts are used for this purpose. When the description of a new case is submitted—typically represented not as text but as a collection of such manually-represented factual features—the program determines which features are present in the new problem, matches it to past cases with similar features, and attempts to map the arguments about the debatable terms from the past cases to the new case. The programs make arguments by analogy that the term is or is not satisfied in the new case based on similar arguments in one or more of the retrieved past cases.

Figure 7 illustrates what a VJAP-type domain model of a dogbite claim’s elements might look like. A domain model is a graph of the elements employed in the legal rules for deciding a type of claim, the factors related to those elements, and the cases in which those factors apply. In the two-thirds of the figure toward the left, one sees the elements of the claim. One of the “OR” elements of the definition of the legal concept of “owner,” c keeps or harbors a , is connected to the set of factors in Figure 6 . The factors are linked to cases in which they apply. For example, factors F6 and F8 are linked to the case of Steinberg v. Petta (i.e., the Steinberg case is indexed by factors F6 and F8).

If the VJAP program had been set up for the dog bite domain with a more complete model of elements, factors, and indexed cases, one could submit the hypothetical scenario to it. One would first have to represent the hypothetical as a list of the factors that apply in the hypothetical. Given a new case, also represented manually as such a list of factors, the VJAP program would follow the factors upward to the associated elements and downward to the indexed cases. Here, arguably, factors F1, F6, and F8 at the right in Figure 7 apply to the hypothetical scenario of Figure 1 . This enables the program to determine that the element “keeps or harbors” is relevant in the problem. Given that factor F1 arguably applies, that is, JC allowed the dog to remain on her property and gave the dog a treat and some water, the conflict with F6 and F8 indicates this element is debatable.

AI approach to Step 6: Searching case law for clarity on questionable elements and sorting through cases for relevance and applicability to the client’s problem

As noted in Part II, Step 6 of this Article, searching case law involves finding cases that are factually similar to the hypothetical involving a non-owner caring for a dog that injures someone. As we saw in the AI approach to Step 2, the top-ten cases retrieved by Westlaw Edge all appeared to be relevant. One would still need to read the cases in order to determine which are the most relevant and how they bear upon the questionable elements for purposes of preparing the memo.

To what extent has AI automated that process of sorting cases by relevance? A search for case law involves many criteria. One is the similarity between the query and documents as measured by some metric such as TF-IDF, a metric proportional to the frequency of a query term in the case document and inversely related to the term’s frequency in the corpus of documents. Other criteria involve query expansion based on identified relationships between words in the corpus, proximity of query terms in case documents, precedential value of a case and treatment history, and frequency of citation of the case in a citation network. While these may not be AI techniques by themselves, services including LexisNexis and Westlaw Edge employ a learning-to-rank approach in which machine learning optimizes the weighting of such criteria given the nature of the search and the evident intention of the searcher and the question the searcher appears to be asking. [65] Analyzing textual queries for intent and for questions asked also involves natural language processing. [66]

Increasingly, text analytic tools are able to determine the issues for which a case has been cited, using a combination of citation networks, machine learning, and natural language processing. For instance, Figure 8 shows the output of the “How cited” tool of Google Scholar Cases for the Steinberg v. Petta case, which, as described above, turned up in a Westlaw search.

The “How cited” tool organizes the cases that cite Steinberg into groups or equivalence classes by the proposition for which they are citing the Steinberg case. Perusing the quotations illustrates the statutory concepts for which the case was cited, including some of the questionable elements in the hypothetical dogbite scenario of Figure 1 . These include “harboring,” “keeping,” and “exercising care, custody, or control” and hint at some relevant facts in the cases for comparing with our scenario.

AI approach to Step 7: Synthesizing a rule from the relevant cases

As noted in Part II, Step 7 of this Article, synthesizing a rule from the relevant cases is a complex task for humans and even more so for AI. It involves 1) organizing the cases as to outcome, 2) analyzing the reasoning in each case to determine the principles or rules the courts used in reaching their decisions, and 3) synthesizing the case rules to formulate a rule that a court in the jurisdiction would apply in the client’s case. Recall the rule that a legal writing professor synthesized in Step 7 for deciding whether a caretaker is an “owner” and thus liable:

If the caretaker voluntarily assumed a significant level of care and control of an animal, similar to the level of care and control a legal owner assumes, such as feeding, providing water, and letting outside, the caretaker is an “owner,” but not if the caretaker performs only smaller actions, like occasionally providing food or water, if not required for the care of the animal; these do not rise to the level of care required for liability.

We know of no program that has ever managed to synthesize this kind of rule from case texts. As noted above, AI and Law programs have barely managed to formulate a rule to summarize the requirements from the text of statutory provisions, much less to summarize the requirements of multiple case texts. [67]

Figure 8 illustrates how Google Scholar Cases organizes cases citing a case whose citation a user has input. The organization is based on a citation network and on some ability to match the sentences that cite a case and their topics. It does not include information about the cases’ outcomes nor does it have any deep understanding of those sentences. It may quote the text of a rule or principle, but it does not understand that this text functions as a rule, a principle, or something else, and it cannot use it to synthesize a rule that would apply to the hypothetical or result in the desired outcome.

AI approach to Step 8: Analogizing and distinguishing searched cases

Similarly, comparing the facts extracted from the texts of cases to those of the text of the dogbite scenario is beyond the ken of existing AI programs. A program can identify matching or similar sentences and infer topics, but it can only infer in a limited way from the text what the facts of a case are, whether they are relevant to the facts of the scenario, or if they are stronger or weaker in favor of the plaintiff in a case or in the scenario. These would be key tasks in analogizing and distinguishing searched cases.

An above section, “AI approach to Step 5: Identifying any questionable elements,” introduced AI and Law work that has modeled legal argument with cases, including analogizing, distinguishing, and citing counterexamples to cases. As noted there, this work has assumed that relevant factors have been manually identified in the facts of the scenario and cases. As we will see in the next section, the analogies drawn by recent computational models of case-based reasoning like VJAP can even account for the values underlying an area of legal regulation and the effects of case decisions on tradeoffs of those values.

Assuming that someone had created a VJAP-type domain model of a dogbite claim’s elements like the one in Figure 7 and populated it with factors like those in Figure 6 and cases represented in terms of such factors, one could imagine a program generating arguments like the following:

→ Where defendant (F6) did no more than merely permit the presence of the animal on his/her premises and (F8) exercised minimal care, custody, or control of the animal, the defendant did not “ keep or harbor an animal” and was not the owner of the animal. Steinberg v. Petta . ß Steinberg can be distinguished. The defendant in the scenario (F1) exercised some measure of care, custody, or control of the animal when she allowed the dog to remain on her property and gave the dog a treat and some water. Where the defendant fed the dog and gave it water, and let the dog out into the yard, the defendant was an “owner” under the Illinois statute. Docherty v. Sadler.

These are some of the kinds of arguments that the programs early in the hypo line (i.e., HYPO, CATO, CABARET, and IBP) could generate based on comparing sets of factors. Again, this assumes that the problem and cases had been manually represented in terms of factors.

Extracting factors automatically from the texts of cases is a challenging research task. [68] Some encouraging progress has been reported in the SCALE project. [69] The researchers developed a scheme for labeling features keyed to the types of finding, issue, factor, and attribute sentences that arise in “domain name” dispute cases under the rules of the World Intellectual Property Organization (WIPO). [70] Their machine-learning approach has achieved some success in automatically identifying instances of such sentences in the texts of previously unseen domain name cases. [71] Another machine-learning approach has achieved some success in predicting factors that are present in the texts of trade secret cases from the VJAP corpus. [72]

In the not-too-distant future, if a traditional legal information retrieval (IR) system is employed and retrieves tens of cases, a legal app might analyze the texts of the cases and identify factors or other features with which it would rerank the cases according to measures of utility given the user’s scenario and goals. This assumes an interface with which the user can specify its goals in a manner that the system understands. In this way, a path is emerging toward connecting commercial legal IR systems with knowledge-based AI approaches, those that explicitly represent and reason with expert knowledge such as legal rules, elements, and factors. [73]

AI approach to Step 9: Predicting the outcome

We saw in Step 9 of Part II of this Article that a good attorney would consider the purpose of the synthesized rule in predicting what the outcome would be if a court applied the synthesized rule:

It seems a likely outcome that JC would not be considered an owner when the attack occurred because her friend dropped off the dog without JC’s knowledge, and JC had not voluntarily assumed owner-like responsibilities for the dog. The attorney would also have to consider and weigh possible counter-arguments—what actions did JC take, like relunctantly allowing the dog to remain and giving the dog water and a treat—that could constitute owner-like care and control. Finally, a thorough attorney would take into account the statute’s purpose—to compel people who have responsibility for an animal, even if not legal owners, to control the animal so that the animal does not injure someone.

This is a kind of reasoning AI and Law has modeled, for example, by the VJAP program, but again, it would only work if it were based on a VJAP-type domain model of a dogbite claim’s elements, complete with factors and cases represented in terms of such factors.

One additional component for VJAP is to represent the values underlying the legal regulation—here the Illinois statute regarding dogbites—and how the various factors affect each value, such as by making it more protected, indicating that it has been waived, making it less legitimate, or interfering with it. For example, two values that one imagines underlie the dogbite regulation are the following:

V1: to limit injuries due to animal bites by incentivizing individuals to exercise control over them. V2: to avoid penalizing people for treating animals humanely.

Case decisions affect tradeoffs across these values. For instance, if the court had come to the opposite conclusion in the Steinberg case, holding that the absentee landlord, who merely allowed his tenants to keep their dog on the premises, was an “owner,” it would strengthen the protection of V1 but, arguably, at the cost of rendering V2 less legitimate. After all, is it fair to hold someone as distantly connected to a tenant’s animal as an absentee landlord responsible for all of the injuries the animal may cause? Perhaps it is, but the court did not so hold, which is part of the significance of the Steinberg decision.

The dogbite hypothetical implicates values V1 and V2. To hold JC liable would strengthen the protection of V1 but at the expense of rendering V2 less legitimate, a tradeoff for which the Steinberg decision could be cited as rejecting. In addition, such a decision would protect V1 at the expense of interfering with V2, penalizing JC for treating a dog humanely by taking care of it and giving it food and water. Thus, the argument above might be continued:

Docherty can be distinguished. The caretaker there had the express responsibilities of feeding the dog, giving it water, and letting it out into the yard. In the current case, JC simply gave the dog a bowl of water and a treat. To apply the result in Docherty would interfere with V2, penalizing someone for treating an animal humanely and would render V1 less legitimate.

If there were a precedent involving that same tradeoff between V1 and V2 in which the court held against liability, JC’s attorney could cite it in support.

The VJAP program begins to model such arguments. It associates factors with values and value effects; thus cases are indexed not only by factors but, in effect, by applicable values and effects on values. The effects on values become a measure of relevant similarity. Given a new problem, VJAP lines up the pro-plaintiff effects and the pro-defendant effects and selects the cases with the most similar tradeoffs. If a case involves the same factors as a problem, this increases the degree of match. Where the factors differ, it may reduce the degree of match to some extent. But those differences in factors might be outweighed by the same tradeoffs in values and such a case might be measured as more relevant than one with the same factors. Whereas CATO and IBP make a fortiori arguments based on set overlaps, VJAP makes the weightiest arguments based on how well a case explains the tradeoffs in the training set of cases in the corpus. [74] This involves factor overlap plus how well a case explains the tradeoffs in weights of value effects. [75]

Based on these weightiest arguments, VJAP predicts the outcome of a case and can explain its predictions in terms of the arguments. As explained above, however, applying VJAP to the dogbite problem would require that someone had assembled a set of factors, values, and cases for this legal domain. Until machine learning can extract factors from the case texts, assembling these items must be done manually.

Legal text analytics offers another way to predict the outcomes of legal cases. Researchers are applying machine learning algorithms, including deep learning neural networks, to predict outcomes of cases directly from textual descriptions of their facts. [76] Neural networks are made up of input and output nodes connected to one or more layers of intermediary nodes via weighted edges. Propagating an input to an output involves a linear combination of the weights. The goal of the network is to learn weights that minimize the deviation of the computed output with the target output. Different architectures of networks, layers, and depths are suitable for different tasks. Deep learning neural networks, which have multiple layers, are organized to learn from sequences of text. [77]

For example, researchers have applied such networks to decisions of the European Court of Human Rights. [78] The machine learning (ML) algorithm predicts if the court found a violation and of which provisions. [79] This would be like submitting a natural language description of the facts, as one does to Westlaw Edge, but with a program now predicting an outcome.

A requirement for applying this text-based ML prediction approach is assembling a large collection of case texts concerning animal bites. Supervised machine learning requires labeled data for training. [80] For example, Chalkidis et al. employed nearly 8,500 cases for training and development and 3,000 cases for testing. [81] One does not need to identify legal knowledge such as elements or issues, factors, and values, as one would for VJAP.

On the other hand, the text-based ML prediction method could not explain its predictions; VJAP can generate such explanations. Although the neural network approach could accurately predict outcomes, without legal knowledge of elements, issues, factors, or values, it would not be able to explain its predictions in terms lawyers are likely to understand. The information the neural networks learn from the large case text corpus is in the form of weights distributed across the network. It does not correspond in any direct way to human legal knowledge and cannot easily be extracted to explain a prediction.

Researchers are attempting to tease out from neural networks the constituents of legal explanations. [82] For example, one kind of neural network approach, hierarchical attention networks (HANs), learns from case decision texts to predict outcomes of new cases and can assign attention scores to the most predictive parts of texts. [83] HANs layer the networks: one layer operates at the word level and extracts predictive words into a sentence representation. [84] Another operates at the level of the resulting sentences and represents predictive aspects of the whole document. [85] For present purposes, the attention model is the important point. It assigns higher weights to the text portions that have greater influence on the model’s outcome prediction.

The hope is that the highlighted portions explain the prediction so that humans can readily understand. [86] Recent experiments with human experts, however, suggest that these highlighted, high-scoring portions of texts fall short of meaningful explanations. [87] In fact, one motivation for the SCALE project, discussed above, [88] was to address this deficiency of explanation using HANs by automatically identifying factors in case texts that could augment explanations of a prediction. [89]

AI approach to Step 10: Writing the office memorandum

The final question is whether an AI program could put all of this information together to write a legal memorandum.

One impetus for this Article involved some surprising recent developments in the ability of programs to generate narratives using language models and transformers. [90] A language model is a neural network that has been trained to predict the next word in a sequence of words. [91] The inputs to the language model are a sequence of words such as, “The defendant cannot be deemed to have harbored or kept an animal , where he was an absentee _______.” Its output is a prediction of the next word in the sequence, for example “landlord.” A transformer, a kind of neural network architecture, can learn associations between words that might be relatively far away from each other in complex sentences. [92] It employs an attention mechanism for this purpose. [93] Given an input sequence, each layer of its network assigns more weight to some features than to others. By making multiple, parallel connections between certain words while ignoring others, it develops a “treelike representation of sentences [which gives] transformers a powerful way to model contextual meaning . . . .” [94] Such a program does not understand the term “absentee landlord,” but its statistical information can predict that “landlord” very likely follows “absentee” in the context of the above sentence.

OpenAI has developed a number of language models including GPT-2 and more recently GPT-3. [95] These are unidirectional models; that is, they read and compile frequency information about associations of words from left to right. [96] Other language models like BERT are bidirectional; they read and compile frequency information from left to right and right to left. [97] GPT-3 learns its frequency information for predicting the next word in a series from a dataset containing an enormous amont of English text extracted from the World Wide Web including Wikipedia, the “Common Crawl,” and Webtext2. [98] Its attention function calculates the probability that a word will appear given the preceding words and stores this frequency information in 175 billion parameters. [99]

A virtue of the OpenAI language models is that they can use their frequency information to generate meaningful sentences. [100] A version of the GPT-2 language model powered an online transformer into which one could submit a narrative to which the transformer will append text. [101]

What happened when we submitted to GPT-2 (i.e., talktotransformer.com ) the description of the dogbite scenario of Figure 1 plus the prompt, “JC consulted her attorney, who advised her . . . .”? It simply appended a few words, for example, “We begin our analysis.” Since the text of the hypothetical apparently was too long to process, we tried a shorter text and examined three responses at the top of Figure 9 . While no first-year law student would be tempted to turn in any of these responses to their legal writing instructor, they are interesting. In each response, the transformer predicted a reasonable appearing, if irrelevant, phrase to complete the last sentence of the input: “JC consulted her attorney, who advised her . . . .” The second and third responses, at least, appeared to deal with “legal” topics. [102]

Input to GPT-2 ( talktotransformer.com ) and GPT-3:

Client JC, an Evanston, IL resident, was caring for a friend’s dog when the dog bit MB. The bite was severe and required multiple stitches. JC consulted her attorney, who advised her

GPT-2’s Response 1: to come up with a “saving alternative” to the dog that would keep her friend’s dog, rather than euthanize it. She came up with the Cattle Dog Boarding Program, which combines the humane treatment of the Cattle Dog (which was her friend’s favorite breed), and the dog’s love of people and children, into one program. MB’s first stay was on the Cattle Dog Boarding Program, which is operated by Operation Metropolitan Assistance Dogs, a nonprofit dedicated to the rescue and placement of dogs from high

GPT-2’s Response 2: to report the incident to the Kennel Club immediately. She immediately contacted the Kennel Club’s hotline, which notified her that the bite was not listed as an on-site incident in the current Kennel Club program. The Kennel Club refused to accept a copy of her kennel contract. As a result, JC sued the Kennel Club and appointed KPMG as her attorney. As a result of this lawsuit, the Kennel Club changed its program to state that a bite does not create a warning report, provided the dog has

GPT-2’s Response 3: to seek immediate professional help. After being told that MB was not a licensed dog trainer, JC called her lawyer’s office to inquire about the status of MB’s certification. At the time, MB was claiming to have worked as a dog trainer and that she had licenses in both Georgia and Texas. JC was informed that she could not obtain MB’s documentation. She then began a direct action campaign in protest against MB and her malpractice. Her legal fees in the ordeal exceeded $150,000. JC’s attorney, Brendan McKenna, obtained the document that demonstrated

GPT-3’s Response: to inform the dog’s owner of the incident. JC emailed the dog owner, but received no response. JC was afraid of being sued, so she gave up her hobby of dog-sitting—though it was a way she earned extra income and enjoyed spending time with friends and their pets. MB turned to Chicago-based Barking Hound Village for help. We sent a demand letter to the dog owner’s insurance company, and were able to negotiate a quick settlement for MB. “I’m so thankful for Barking Hound Village,” said MB. “They were there for me every step of the way.”

By contrast, GPT-3 is accessible only by application to OpenAI. Eight months later (in April 2021), after OpenAI granted GPT-3 access to a colleague, we asked him to submit the same queries. For the shorter query, GPT-3 generated the response at the bottom of Figure 9 . It is just as fanciful as those of GPT-2, although it does focus on the possibility that JC could be sued.

One sign of progress, however, was that GPT-3 could process the longer query consisting of the full hypothetical scenario of Figure 1 and the prompt, “JC consulted her attorney, who advised her . . . .” GPT-3’s response is shown in Figure 10 . The first paragraph is remarkable for a number of reasons. First, GPT-3’s completion of the prompt seems apt; it appears to be a reasonable facimile of legal advice. Second, it is tailored to the circumstances of the hypothetical. Unlike question answering systems, GPT-3’s response specifically refers to JC and MB in their roles in the hypothetical. Third, although GPT-3 does not cite legal sources such as Illinois statutes or cases to anchor its advice, it does quote two legal phrases in an apparently appropriate way: “unreasonable risk to human safety” and “loss of a normal life.” While there is no indication of where these phrases came from, a Google search indicates that the former phrase appears in materials concerning hazardous materials and the latter in Illinois jury instructions concerning damages. [103] It also appears in a website for a Chicago dog bite lawyer. [104]

Input to GPT-3: Client JC, an Evanston, IL resident, was caring for a friend’s dog when the dog bit MB. Although JC had cared for the dog in the past, on the day that the attack occurred, the friend had dropped off the dog in JC’s backyard without asking JC. JC reluctantly allowed the dog to stay, seeing no choice in the matter, and gave the dog a bowl of water and a treat. JC had a scheduled party while the dog was still in her care and the dog bit a guest, MB, when MB dropped a plate of chicken and the dog went for the chicken. The bite was severe and required multiple stitches. JC comes to the attorney somewhat distressed about the situation and wants to know if she could be liable to MB. JC consulted her attorney, who advised her

GPT-3’s Response: that she could potentially be liable for MB’s injuries based on the fact that she was still in possession of the dog while it was an “unreasonable risk to human safety.” The attorney advised JC to contact a dog bite attorney. At the time of the dog bite, MB was a guest in JC’s home. MB has a claim against JC for the injuries he sustained. MB may be able to recover for the injuries that he has sustained, as well as any future complications that may arise from his injuries. MB can seek damages for his medical bills and for his pain and suffering. MB may also be able to recover damages for his “loss of a normal life.” This includes his loss of earnings and loss of future earnings. MB may be able to recover for his lost future earnings.

If you were bitten by a dog or if you sustained any other injuries from dog bites or dog attacks, contact a dog bite attorney.

Dog Bite Lawyer in Chicago, Evanston, and Skokie IL

Dog bites are a serious matter and can cause serious injuries. If you or your child has been bitten by a dog, you should seek the advice of a dog bite lawyer. If you live in the Chicago area, you can contact Chicago Dog Bite Attorney, Jason A. Bendoff. Jason has helped many individuals recover compensation for their injuries, including dog bites and dog attacks. He has recovered over $5 million for his clients.

Contact a Chicago Dog Bite Attorney

If you would like to discuss your case with a Chicago dog bite lawyer, Jason Bendoff, call (847) 585-7378 or contact him online.

Despite GPT-3’s impressive performance, no attorneys need fear for their jobs, at least not yet. GPT-3’s output is far from a legal memorandum. It does raise the question, however, of whether and how GPT-3 could be trained to write a legal memorandum. As it happens, GPT-3 can learn to perform some tasks when provided a natural language prompt that contains even just one or a very few training examples. This “few-shot ‘in-context’ learning . . . allows users—even those without technical expertise” to retrain the learning model. [105] It will be interesting to see if and how one can train GPT-3 to improve its response by modifying the prompt and providing examples.

In the meantime, some new legal apps may be helpful in reviewing a draft legal memorandum. One can submit a draft memo to an AI program like Casetext’s CARA A.I. to obtain suggestions about additional cases to cite. In the discussion of the “AI approach to Step 2,” we submitted the dogbite scenario to Casetext by cutting and pasting the Figure 1 hypothetical into the search box. As noted, one can also upload a brief via the “Search with a document” feature in order to find legally and factually relevant cases with Casetext’s CARA A.I. [106] Upon submitting the completed draft of a memo in the Appendix (on May 24, 2022), the program responds: “What issue or fact do you want CARA A.I. to focus on? Enter an issue or fact . . . .” It suggests various issues, including, “animal control acts,” “standard of care,” “duty of care,” “legal owner,” “civil damages,” as well as offering “all suggested cases.” Upon selecting “legal owner,” it provided “[t]op cases recommended by CARA A.I.,” noting that the “[r]esults [are] contextualized to the Legal Memorandum.pdf [Appendix] and your search terms.” A number of the top-ten cases appeared to be useful. CARA A.I. probably suggests them based on citation networks and issue topics of paragraphs containing citations.

Westlaw Edge’s Quick Check [107] and Lexis+ Brief Analysis [108] are similar tools. Upon uploading a draft brief or memo, each generates a report. Quick Check’s report recommends cases and other sources for each named section of the memo, provides warnings about cited sources, and analyzes quotations for accuracy. Its five recommended cases all related to the issue of ownership of the dog and had not already been cited in the memo. In addition, it recommended two briefs as similar to the submitted memo. Brief Analysis extracted twenty-five concepts from the memo including Ownership, Legal Owner, and Assume Control. From the twenty-seven recommended cases and seven treatises, it quoted at least fifteen relevant passages on the issue of ownership from cases not included in the memo.

AI legal apps are moving in the direction of automatically generating memoranda of law. Based on CARA A.I., Casetext’s Compose is generating first drafts of memoranda supporting particular types of motions, for example, motions to “quash a subpoena, exclude expert testimony, file a motion for protective order or compel discovery or disclosure.” [109] Presumably, each type of motion has an associated template that provides a framework of issues and boilerplate language for automatically generating textual arguments citing jurisdictionally appropriate statutes and cases relevant to each of the issues. Given the apparent limitations of language-model-based generation of narratives, such frameworks are probably necessary if they are to generate legal memoranda.

What will it take for transformer language models to generate better narratives than we saw in Figures 9 and 10 ? For one thing, the corpora on which GPT-2, GPT-3, and other language models have been trained probably do not (yet) include legal decisions and memoranda. It would be interesting to see what the GPT-3 language model could accomplish with additional training and a more relevant corpus. [110] Nevertheless, “the hurdle to generate authentic long texts is still high.” [111] The legal memorandum in the Appendix is over 3000 words long, while the most relevant part of GPT-3’s response is less than 150 words.

For another reason, even if GPT-3 had access to legal decisions and memoranda, there is still the problem that “machines don’t really understand what they’re writing (or reading).” [112] This is problematic, since GPT-3 can create snippets whose “style is [so] legalistic and facially convincing” that despite its “suspicious content,” “legal experts . . . are . . . uncertain about determining whether a legal opinion [snippet] is machine-generated or written by humans.” [113]

Transformer language models lack the conceptual structures that humans employ in reading or writing domain-specific texts. In Part II of this Article, we saw how humans would write a memo like that of Appendix A, or at least, how we would teach first-year law students to do so. In describing the steps of this process, it is natural to refer to conceptual legal categories and structures. These include, but go beyond, such legal claim- or statute-specific topics as “provocation,” “owner,” “harboring,” “care,” “custodian,” or “knowingly permit.” They include concepts for working with “legal regulation,” such as “statute,” “statutory law,” “case law,” “governing law,” or “legal rule” and rule “elements.” In addition, they include the working concepts and structures of interpreting and arguing about what legal rules mean and how they apply to facts, such as “relevant facts,” “legal question,” “questionable” elements, “synthesizing” a rule, “analogizing” and “distinguishing” cases, and “office memorandum.” They also include common sense concepts about which the programs have no knowledge, such as dogbites, care for dogs, the nature of dogs and human behavior with respect to dogs, or owning a dog. Finally, as noted above, the programs have no knowledge of the distinction between legal concepts and their common sense “counterparts,” such as “owner” as defined in the statute versus “owner” in common parlance. [114]

Concepts and structures like these are a necessary part of the way we describe how humans would read, understand, or write a memo like that of the Appendix. We would naturally speak of readers or authors as identifying, applying, and manipulating patterns of these concepts and structures in order to create or interpret the text. [115]

Presumably, these cognitive models arise through education. Law students may learn to identify, apply, and manipulate such patterns of conceptual structures through repetition and practice in law school; in a sense they may tune their more general models of reading and language to the demands of the legal domain. [116]

Can language models and transformers work if they do not understand the conceptual structures that law students learn to use? Can exposure even to millions of examples of legal memoranda or decisions enable programs to develop cognitive models or their machine equivalents? Or, can an extended series of well-designed few-shot training episodes enable a transformer model to learn to construct a legal memorandum like that in the Appendix? Perhaps eventually, but as yet, that does not seem to be the case.

IV. Implications for Teaching Legal Writing

All of this leads us to a few tentative conclusions about the implications of the development of AI and Law for the teaching of legal writing. It should be clear that AI is not poised to take over entry-level law positions. AI is not in the foreseeable future going to replace lawyers. It might be, however, that lawyers familiar with and facile with AI will replace lawyers who are not. How do we as legal educators, and specifically as legal writing teachers, introduce students to the ways that AI can now make their work more efficient and more accurate? It seems to us that there are at least two areas worth exploration.

First, and more importantly the impetus for this Article, the legal writing classroom needs modifications to introduce students to and to incorporate the possibilities of AI contributing to the task of writing an office memorandum (and perhaps other basic documents). Here, for example, is one of many possible ways in which students working with AI might work through the steps required to write an office memorandum:

Hybrid Step 1. Manually develop statement of hypothetical and/or frame legal question.

Hybrid Step 2. Submit full-text hypothetical in natural language query to Westlaw Edge or Casetext, or submit framed legal question to ROSS-type question answering system (if available).

Hybrid Step 3. Read Westlaw Edge, Casetext outputs of cases and statutes to see how they frame the legal question and bear upon it.

Hybrid Step 4. Manually pull out macro rule’s elements. Casetext’s CARA A.I. may indicate issues (for a submitted draft memo) as may Lexis Answers (if applicable).

Hybrid Step 5. Manually apply client’s facts to the elements.

Hybrid Step 6. Manually identify any questionable element given hypothetical’s facts. Following up on Casetext’s CARA A.I.'s issues (for a submitted draft memo) may indicate questionable elements.

Hybrid Step 7. Manually search with keywords case law from Westlaw Edge or Casetext to find cases that are factually similar to the hypothetical involving a non-owner caring for a dog that injures someone. Read these cases in order to determine which are the most relevant and how they bear upon the questionable elements for purposes of preparing the memo.

Hybrid Step 8. Manually synthesize a rule from the multiple relevant cases.

Hybrid Step 9. Manually analogize and distinguish searched cases (comparing the client’s facts to the facts in the cases).

Hybrid Step 10. Manually predict the outcome in the hypothetical.

Hybrid Step 11. Manually write the office memorandum. Optionally, upload drafts to Casetext’s CARA A.I., Westlaw Edge Quick Check, or Lexis+ Brief Analysis for suggestions of additional issues or cases.

This hybrid process for writing a legal memorandum is not radically different from the above ten-step process for (manually) preparing a legal memo. [117] Instructors can integrate the use of AI tools into the process while preserving the narrative description of cognitive models of legal reasoning: identifying facts, applying them to elements, synthesizing a rule from relevant cases, and analogizing and distinguishing cases.

Second, the legal writing classroom should convey some basic instructional overview of emerging possibilites for AI and Law-related jobs, such as the “human experts” or system designers who organize and manage the reading, analysis, and annotation of a corpus of statutory and case law. What we do know for sure is that new attorneys will need familiarity with AI techniques because AI will be increasingly utilized in law practice, and the machine learning involved requires extensive human intervention; someone must define the task that machine learning will perform, assemble and preprocess the data, design the types of classifications to be made, label (or annotate) a training set of data in terms of theses classifications, apply the machine learning algorithm, evaluate the results, and investigate the errors. A technical staff person may perform much of that, but not without the collaboration of attorneys who understand the technology as well as how to apply it in solving legal problems, how to evaluate the results, and whether to rely on them. Teaching those skills and knowledge to law students will require a paradigm shift in the discipline of legal writing, just as adapting to the dominance of computer-assisted legal research has required a paradigm shift in the teaching of legal research. It might well be that students who cannot effectively interact with and use AI will be ill-prepared for law practice.

Third, legal writing professors might fruitfully collaborate with other law professors and computer scientists who are already developing and teaching courses designed to introduce law students to the possibilities of AI in law practice. One example is the course that one of the authors of this Article is already teaching. Here is a brief description:

At the University of Pittsburgh School of Law, the author (a law professor) and a computer scientist co-teach a semester-long course entitled “Applied Legal Analytics and AI” to a class combining law students and undergraduates or graduate students in computer science or engineering. [118] The course introduces students to applying machine learning and natural language processing to extract information from legal textual data and provides gradual practice in tackling incrementally more complex tasks. Students experience the ways that text analytics have been applied to support the work of legal professionals and the techniques for evaluating how well they work. The course culminates in small team projects in applying machine learning and data analytics to legal problems.

As an example of integrating legal writing instruction and text analytics, the first homework assignment introduces students to using a legal question answering system in an exercise in legal research and memo writing. The LUIMA system, a prototype legal question answering system one of the instructors developed, accepts questions dealing with veterans’ claims for compensation for posttraumatic stress disorders (PTSD) and retrieves answers (i.e., extracted sentences similar to the question) from a database of decisions of the Board of Veterans Appeals. As a way to introduce the non-law students to some legal system basics, and as a refresher for the law students, they all read excerpts from an informative text authored by two veteran legal writing instructors. [119] The excerpts cover reading and briefing cases, using statutes, synthesizing cases, and drafting a legal memorandum and introduce basic legal concepts such as burden of proof, standard of proof, presumption, and preponderance of the evidence. With this as a guide, students read and brief a decision of the Board of Veterans Appeals, access LUIMA to answer legal questions about a problem scenario, and use the results of their legal research with LUIMA to write a short legal memorandum analyzing the problem.

In this way, the first homework assignment gives students a chance to work with a basic AI legal question answering system and to experience using the system to perform legal research and writing. In the remainder of the course, they learn the basics of how such a legal question answering system works.

V. Conclusions

Experienced legal writers understand the tools available for research, and for each tool they develop a sense of the information that tool is likely to find and the information it may miss. Legal writing instructors introduce law students to these tools and help them to begin to appreciate their utility, their strengths, and their limitations. With the advent of AI tools and the application of text analytics to legal documents, it has become considerably harder to understand how the tools work and how to assess their results, especially in the face of extraordinary claims for their capabilities.

In this Article, we have attempted to apprise legal writing instructors about how these tools can be applied, what they can do, and what they cannot do. We have illustrated some ways in which the tools could be integrated into the familiar lessons in legal writing. Our hope is that this suggestion of the melding of traditional legal writing teaching and AI will open a much larger conversation about how we might introduce the possibilities of using AI to our legal writing students.

To: Supervising Attorney From: Associate Date: October 5, 2019 Re: Jaime Castro’s liability under Illinois’s Animal Control Act

QUESTION PRESENTED

Under the Illinois Animal Control Act, is Jaime Castro liable for injuries Matt Bevers sustained when a friend’s dog, left on Castro’s property without her knowledge or explicit consent, bit Bevers’s hand?

BRIEF ANSWER

Probably no. Castro will not be liable for the injuries Bevers sustained. The Illinois Animal Control Act holds the owner of the animal liable in civil damages for any animal attacks or injuries as long as the animal, without provocation, attacks, attempts to attack, or injures any person who is peaceably conducting themself in any place where they may lawfully be. An owner is defined as someone who knowingly and voluntarily consents to care for an animal, even if not the legal owner. In this case, the dog attacked Bevers without provocation while Bevers peaceably conducted himself at the party to which Castro invited him. A court will likely hold, however, that Castro is not liable for Bevers’s injuries because she did not voluntarily assume responsibility to manage, care for, or control the dog in a manner that owners would generally be accustomed, regardless of the amount of time the dog had been in her care previously.

Our client, Jaime Castro, anticipates that Matt Bevers will sue her. Bevers, a professional videogamer, claims he will sue for injuries sustained from a dog bite he received on Castro’s property.

Castro lives in a home with her housemate, Ilana Wexler. Their friend, Abbi Abrams, has a greyhound licensed in Abrams’s name. Oftentimes, Abrams would leave her dog at Castro’s and Wexler’s residence. Castro and Wexler kept dog treats for Abrams’s dog, indicating the frequency that Abrams would leave her dog there.

Castro planned to have a viewing party on August 5, 2019, for the Cubs-White Sox series. She left earlier in the day to the grocery store, and she returned home around 3 p.m. At home, she found Abrams’s dog alone in the backyard. She had not known that Abrams was going to leave the dog that day. She provided the dog with a treat and some water.

Because the party would be happening in her backyard, Castro kept the dog indoors and closed the doors to the house. She placed a sign on the front door that indicated to guests to go around the house to the back to enter the party.

Guests arrived at the party, and they all entered the backyard through the back of the house instead of through the front door. Bevers arrived with a plate of chicken, and unlike the other guests, he entered the home through the front door. As he exited the home to the backyard, the dog ran between his legs causing him to lose his balance and drop the chicken. The dog tried to eat the chicken but instead bit Bevers’s hand. From the bite, Bevers sustained an injury to his thumb and index finger, causing an injury that required Bevers to receive seven stitches in his hand.

Bevers threatened to sue Castro for damages, including his medical bills, as well as the losses incurred from his inability to play videogames as a result from his injury.

The Illinois Animal Control Act seeks to encourage tighter control on animals to protect the public from harm. Docherty v. Sadler , 689 N.E.2d 332, 334 (Ill. App. Ct. 1997). The statute explains what qualifies as an animal attack:

If a dog or other animal, without provocation, attacks, attempts to attack, or injures any person who is peaceably conducting himself or herself in any place where he or she may lawfully be, the owner of such dog or other animal is liable in civil damages to such person for the full amount for the injury proximately caused thereby.

510 Ill. Comp. Stat. Ann. 5/16 (West 2006).

A plaintiff must show that the animal attack occurred while they peaceably conducted themself, that they did not provoke the animal, and that they were in a place they could lawfully be. In the present case, the encounter between Bevers and the dog satisfies the elements that qualifies an attack under the statute. Bevers peaceably conducted himself at the time of the incident. He entered the home through the front door and exited to the backyard through the back door in order to enter the party. Bevers did not provoke the dog when it bit him. He dropped a plate of chicken, and when he reached to pick it up, the dog bit his hand while attempting to eat the chicken. Castro invited Bevers to the party, so he lawfully could be there. Thus any person who qualifies as the dog’s owner is likely liable to Bevers.

The question remains whether Castro qualifies as an owner under the Illinois Animal Control Act. The statute provides a definition of an owner:

Owner means any person having a right of property in an animal, or who keeps or harbors an animal, or who has it in his care, or acts as its custodian, or who knowingly permits a dog to remain on any premises occupied by him or her.

510 Ill. Comp. Stat. Ann. 5/2.16 (West 2006). Furthermore, Illinois courts have required more than passive involuntary care. Instead, for owner liability, they require that a person voluntarily care for the animal when an injury occurs and that the person actively demonstrate the care by an act such as feeding. Thus, a court will probably not hold Castro liable for the injuries Bevers sustained from the dog attack because she did not voluntarily assume responsibility to manage, control or care for the dog in a manner that owners would generally be accustomed.

A. Under the Illinois Animal Control Act, Jaime Castro does not qualify as an “owner” because she did not voluntarily care for the dog when the bite occurred.

Illinois case law establishes that an individual qualifies as an owner of an animal if they voluntarily assume a measure of responsibility to care for an animal and have the responsibility to manage or exert their control over the animal in a manner to which owners would generally be accustomed, regardless of the amount of time the animal is in the person’s care or the person’s previous interactions with the animal. Care consists of providing food, water, and letting the animal outside, which constitutes more than passive ownership of the animal. Steinberg v. Petta , 501 N.E.2d 1263, 1265 (Ill. 1986); Beggs v. Griffith , 913 N.E.2d 1230, 1235 (Ill. App. Ct. 2009); VanPlew v. Riccio , 739 N.E.2d 1023, 1024 (Ill. App. Ct. 2000); Severson v. Ring , 615 N.E.2d 1, 4 (Ill. App. Ct. 1993); Docherty , 689 N.E.2d at 334.

Illinois courts require a measure of care and custodianship that demonstrates more than passive ownership of the animal in order to be the owner. Steinberg , 501 N.E.2d at 1266; Severson , 615 N.E.2d at 4. In Steinberg , the court held that the defendant did not qualify as an owner when he, an absentee landlord, allowed his tenants to keep a dog on the premises, and the dog bit the plaintiff. Steinberg , 501 N.E.2d at 1266. The court characterized the allowance of the dog on the premises as “passive ownership,” which did not satisfy the measure of care as dog owners customarily assume. Id . Similarly, in Severson , the court held that the defendant did not qualify as an owner when she allowed a friend to chain his dog to a tree in her backyard, and it attacked a child on her property. Severson , 615 N.E.2d at 4. Though the defendant and her boyfriend checked the dog’s food and water, they did not need to for its care. Id at 3. The court reasoned that because the defendant did not need to provide food or water, nor do anything necessary for the care of the dog, she did not fulfill the measure of care for an owner. Id .

The measure of care pursuant to ownership includes feeding the animal, providing water, and letting the animal outside. VanPlew , 739 N.E.2d at 1026; Docherty , 689 N.E.2d at 335. In VanPlew , the court held that the plaintiff met the standard of care that made her an owner under the statute when she assumed the responsibilities of feeding the dog, giving it water, and letting it outside while its legal owner went on vacation. VanPlew , 739 N.E.2d at 1025. While fulfilling her responsibilities towards the dog, it bit her. Id . The court held that because she had the specific responsibilities of care towards the dog including providing it with food and water, and letting it outside, she provided necessary care, and undertook custody in a manner that owners would generally assume. Id . at 1026. Similarly, in Docherty , the court held that the plaintiff qualified as an owner when a dog belonging to his absent neighbor injured him while under the plaintiff’s care and control. 689 N.E.2d at 333. The court held that because he had the express responsibilities of feeding the dog, giving it water, and letting it out into the yard, he had the “status of owner.” Id . at 335.

To be an owner, Illinois courts include voluntariness as an element to an individual’s care, custody or control over the animal. VanPlew , 739 N.E.2d at 1026; Docherty , 689 N.E.2d at 335. The court in VanPlew held that the plaintiff qualified as the owner when she took the job to pet sit for the defendant while the defendant travelled. 739 N.E.2d at 1024. The court reasoned that because the plaintiff voluntarily placed herself in a position of control akin to an owner, she had custody over the dog at the time of the injury. Id . at 1026. Similarly, the court in Docherty held that the plaintiff had ownership of the dog when he explicitly agreed to take on the responsibilities of care for the defendant’s dogs while the defendant traveled. 689 N.E.2d at 333. The court reasoned that because he voluntarily took control of the dogs, he had custody over them at the time of injury. Id . at 335.

Although no Illinois courts have ruled over a case in which a party had involuntary care or control over an animal, the defendant in Rodriguez v. Cordasco , a New Jersey case, did not expressly assume control over stray dogs on her property, and the court found that the defendant did not qualify as the owner under the New Jersey statute. 652 A.2d 1250 (N.J. Super. Ct. App. Div. 1995). The stray dogs merely remained on her property, and she sporadically fed them, and, therefore, she did not "owe a duty of care to the public to protect against the action of those dogs." Id. at 1252. When the stray dogs ran from her property and chased the plaintiff, she did not have liability over them. Id . The court reasoned that the defendant’s sporadic feeding did not make her an owner or qualify her as a keeper of the dogs because she did not expressly assume management, care, or control over the dogs. Id . at 1253.

If someone voluntarily assumes control or management of an animal and does not exercise that ability to control or manage an animal to the degree an owner would be accustomed, he or she is liable as an owner. Beggs , 913 N.E.2d at 1237. In Beggs , the court held that the defendant had the status of owner when a prospective buyer of his property sustained injuries on his property from the defendant’s friend’s horses. Id . The defendant voluntarily gave his friend’s horses access to his land and barn for their care while still maintaining the ability to control when the horses could be on his property. Id . at 1236. The court reasoned that because he chose not to exercise his control over the horses by preventing them from having access to his barn when the plaintiff visited, and because he facilitated the plaintiff’s visit, he qualified as an owner. Id at 1236–37. Conversely, in Rodriguez , the New Jersey court ruled that the defendant’s actions of feeding the stray dogs did not give her the duty to assume control over them to protect the public, so she did not have to exert control over the dogs as the plaintiff passed her house. 652 A.2d at 1252.

Castro’s care and custodianship of the dog could be characterized as passive ownership by Illinois courts. In Steinberg , the court held that the defendant was not an owner because he merely allowed his tenant’s dog to remain on the premises. 501 N.E.2d at 1266. Similarly, at the moment of the attack, Castro merely allowed the dog to remain on her property, so as in Steinberg , a court will likely hold that this level of care does not fulfill a measurement of care for the dog beyond passive. Bevers could argue that unlike the defendant in Steinberg, Castro did provide some care to the dog when she gave it a treat and water. However, Castro providing the dog with a treat and water does not provide a dog necessary care pursuant to ownership. Similarly, the court in Severson ruled that the defendant was not the owner because she did not need to provide food or water, nor do anything necessary for the care of the dog besides allow it to remain chained in her backyard. 615 N.E.2d at 4. A court will likely hold that Castro is not an owner because, like the defendant in Severson , she did not need to provide a treat and water to the dog for its care.

The level of care that Castro gave the dog does not fulfill the standard that Illinois courts established for an owner including feeding the animal, providing water to the animal, and letting the animal outside. The courts in VanPlew and Docherty ruled that the plaintiffs were both owners because they assumed the responsibilities of feeding the dogs, giving them water, and letting them outside, so they fulfilled the standard of care necessary to be an owner. VanPlew , 739 N.E.2d at 1024; Docherty , 689 N.E.2d at 334. Conversely, Castro only provided the dog with water and a single treat. Bevers could argue that this constituted a level of care that an owner would be accustomed to giving. However, Castro did not let the dog out as in the cases of VanPlew and Docherty . Once she brought the dog inside the home, she did not let him out for his care. Also, it can be argued that a treat does not qualify as food akin to the substantive food provided to the dogs by the plaintiffs in VanPlew and Docherty . Courts would likely hold that she does not qualify as an owner because unlike the plaintiffs in VanPlew and Docherty , she did not fulfill all three elements of the measure of care pursuant to ownership.

Castro does not qualify as an owner of the dog because she did not voluntarily assume care, custody, or control over the dog. In both VanPlew and Docherty , the plaintiffs placed themselves in positions analogous to owners when they voluntarily assumed the roles as pet sitters while the legal owners were not home. VanPlew , 739 N.E.2d at 1024; Docherty , 689 N.E.2d at 334. The plaintiffs in these cases voluntarily took on these roles with express knowledge of their duties of care towards the dogs, so the courts found them both liable as owners under the statute. VanPlew , 739 N.E.2d at 1024; Docherty , 689 N.E.2d at 334. In VanPlew , the plaintiff had an agreement to provide her services of care to the dog for money. VanPlew , 739 N.E.2d at 1024–23. Conversely, Castro did not give express agreement to care for the dog when she came home and found the dog in her backyard. Bevers could argue that Castro, unlike the plaintiffs in both Docherty and VanPlew , had cared for the dog on occasions previously, so she gave implicit consent for the care of the dog. Illinois courts have not considered a case involving involuntary care of a dog; in a New Jersey case, however, a court did not hold the defendant liable for dogs when they chased the plaintiff, although the defendant had a history of providing food for stray dogs on her property. Rodriguez , 652 A.2d at 1252. The court in Rodriguez ruled that feeding the dogs when they would come on property did not constitute ownership. Id . at 1252. Similarly, Castro did provide care for the dog in the past, but she, like the defendant in Rodriguez , did not give express consent to the dog being on her property at the time of the attack, so Illinois courts may rule that she is not an owner.

Castro did not voluntarily assume control over the dog, but she did exercise her ability to control the dog in order to protect her guests, so she should not be liable as an owner of the dog at the time of the attack. In Beggs , the court held that the defendant was an owner because he did not exercise his control over the horses on his property to prevent them from accessing his barn when he knew the plaintiff would be on his property. Beggs , 913 N.E.2d at 1236. In addition, the defendant solicited the plaintiff as a potential buyer of his property, so he placed her on in the same location as the horses that harmed her. Id at 1236–37. Similarly, Castro invited Bevers to her party, but unlike the defendant in Beggs , Castro did not assume control voluntarily, and she did exercise her ability to control the dog to protect her guests. Castro controlled the dog by keeping him inside the house to prevent interaction between the dog and the guests attending the party in the backyard. In addition to her control over the dog’s location, Castro placed a sign on the front door indicating to guests to enter the party through the back of the house, supporting her intention to keep the dog away from the guests. It can be argued that Castro did not have a duty to control the dog, and she provided a public service by trying to control the dog. The court in Rodriguez held that the defendant had no duty to protect the public by assuming control over the stray dogs. Similarly, Castro found the dog on her property upon returning home, and she had no duty to protect her guests from it. Illinois court will likely hold that Castro does not qualify as an owner because she did not voluntarily assume control over the animal, so she did not have the duty to control the dog.

The Illinois Animal Control Act holds animal and dog owners liable to civil damages if the animal attacks another person. Castro can concede that the dog attacked Bevers without provocation while Bevers peaceably conducted himself in a place that he could lawfully be. She will probably be able to establish that she is not the legal owner of the dog under the Animal Control Act even though the dog was on her property. She can establish that she did not provide adequate care in a manner that would generally be assumed by an owner. She can argue that the dog was there without her consent so she involuntarily cared for it. Finally, Castro did not voluntarily assume control over the dog but did attempt to control it by keeping it indoors. She intended to keep the dog away from the guests by keeping the dog indoors and by placing a sign on the front door to keep the guests from entering the home. For these reasons, Castro was not the legal owner of the dog at the time the attack occurred, and she should not be held liable under the Illinois Animal Control Act.

Paul D. Callister, Law, Artificial Intelligence, and Natural Language Processing: A Funny Thing Happened on the Way to My Search Results , 112 Law Libr. J. 161, 172 (2020) (“Brief analysis is also a feature of Westlaw Edge, Casetext, Ross Intelligence, and several other vendors’ products. Actually writing the brief may not be far behind.”).

John McCarthy, Marvin L. Minsky, Nathaniel Rochester & Claude E. Shannon, A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence, August 31, 1955 , 27 AI Mag ., no. 4, at 12, 12 (2006).

Kevin D. Ashley , Artificial Intelligence and Legal Analytics: New Tools for Law Practice in the Digital Age 4 (2017).

Id . at 5; see also Kevin D. Ashley, Automatically Extracting Meaning from Legal Texts: Opportunities and Challenges, 35 Ga. St. U. L. Rev. 1117, 1117 (2018).

Zhi-Hua Zhou, Machine Learning 2 (Shaowu Liu trans., 2021).

Ryan Whalen, Legal Networks: The Promises and Challenges of Legal Network Analysis, 2016 Mich. St. L. Rev . 539, 548–52 (2016). The Ravel tool, now part of LexisNexis’s Context, employs citation networks. Ravel Law , https://www.ravellaw.com/ [ https://perma.cc/Q6P3-5RWA ] (last visited Apr. 30, 2021).

John Prager, Eric Brown, Anni Coden & Dragomir Radev, Question-Answering by Predictive Annotation, in SIGIR '00: Proceedings of the 23 rd Annual International ACM SIGIR Conference on Research & Development in Informational Retrieval 184, 184 (2000).

ROSS Intelligence , https://rossintelligence.com [ https://perma.cc/7LAK-H4GW ] (last visited Apr. 30, 2022). See infra note 32 and accompanying text.

See Ivy Wigmore, Artificially-Intelligent Attorney (AI Attorney) , https://www.techtarget.com/searchenterpriseai/definition/artificially-intelligent-attorney-AI-attorney [ https://perma.cc/K4AQ-A4XP ] (last visited Apr. 30, 2022); Dana Remus & Frank Levy, Can Robots Be Lawyers? Computers, Lawyers, and the Practice of Law , 30 Geo. J. Legal Ethics 501, 503 (2017).

Michael Simon, Alvin F. Lindsay, Loly Sosa & Paige Comparato, Lola v. Skadden and the Automation of the Legal Profession, 20 Yale J.L. & Tech . 234, 237 (2018).

See, e.g. , Victoria Hudgins, Casetext Launches New Brief-Writing Automation Platform Compose , Legaltech News (Feb. 25, 2020, 5:00 AM), https://www.law.com/legaltechnews/2020/02/25/casetext-launches-new-brief-writing-automation-platform-compose/ [ https://perma.cc/V7YK-VUXV ]. AI’s memo writing capabilities are discussed in Part 3 of this Article, in the section “AI approach to Step 10: Writing the office memorandum.”

Legal writing teachers may slightly vary these steps; what is laid out here offers a basic template for the skills involved.

Obviously this activity can occur in a number of ways: for example, a client interview or an assignment from a senior attorney. Here we are simplifying and imagining that the facts come directly from a client.

Steinberg v. Petta, 501 N.E.2d 1263 (Ill. 1986); Beggs v. Griffith, 913 N.E.2d 1230 (Ill. App. Ct. 2009); Van Plew v. Riccio, 739 N.E.2d 1023 (Ill. App. Ct. 2000); Docherty. Sadler, 689 N.E.2d 332 (Ill. App. Ct. 1997); Severson v. Ring, 615 N.E.2d 1 (Ill. App. Ct. 1993). A good researcher might also find an out-of-state case that deals with the issue of involuntary care since JC’s lack of voluntariness in caring for the dog on this occasion could be important. Here, Rodriguez v. Cordasco, 652 A.2d 1250 (N.J. Super. Ct. App. Div. 1995).

See generally Marc Queudot, Eric Charton & Marie-Jean Meurs, Improving Access to Justice with Legal Chatbots, 3 Stats 356 (2020), https://doi.org/10.3390/stats3030023 [ https://perma.cc/55FN-4YQD ].

Dong Yu & Li Deng, Automatic Speech Recognition: A Deep Learning Approach 307 (2015) (“ASR [Automated Speech Recognition] systems still perform poorly . . . even given the recent technology advancements . . . with spontaneous speech in which the speech is not fluent, with variable speed or with emotions.”).

Armin Seyeditabari, Narges Tabari & Wlodek Zadrozny, Emotion Detection in Text: A Review, arXiv (June 2, 2018), https://arxiv.org/pdf/1806.00674.pdf [ https://perma.cc/DKV3-3VF7 ]. See also Ashrita R. Murthy & K. M. Anil Kumar, A Review of Different Approaches for Detecting Emotion from Text , IOP Conference Series: Materials Science & Engineering , 1110 012009 (2021), https://iopscience.iop.org/article/10.1088/1757-899X/1110/1/012009 [ https://perma.cc/3U9G-PND7 ] (last visited Apr. 30, 2022).

Johannes Dimyadi, Sam Bookman, David Harvey & Robert Amor, Maintainable Process Model Driven Online Legal Expert Systems , 27 Artificial Intelligence & L. 93, 93 (2019).

Services such as Neota Logic and A2J Author can assist in creating the expert systems and authoring the rules. See Neota, https://www.neotalogic.com/ [ https://perma.cc/GK2V-EYRB ] (last visited Apr. 30, 2022); A2J Author, https://www.a2jauthor.org/ [ https://perma.cc/AQ87-UNGZ ] (last visited Apr. 30, 2022). Law school clinics employ online expert systems to screen potential clients and record information about their legal problems. See Roger V. Skalbeck, Tech Innovation in the Academy , in AALL & ILTA Digital White Paper: The New Librarian 74, 77 (2012), http://epubs.iltanet.org/i/87421-the-new-librarian/72?m4= [ https://perma.cc/6ZEP-8WZW ]; see also Ronald W. Staudt & Andrew P. Medeiros, Access to Justice and Technology Clinics: A 4% Solution , 88 Chi.-Kent L. Rev. 695, 716 (2012) (advising that “new attorneys will need to be familiar with the processes involved in building legal expert systems”). Neota Logic features examples of web-based expert systems that guide clients to appropriate law firm resources or personnel for various types of claims. See https://demo-portal.neotalogic.com/a/home [ https://perma.cc/N7SV-BEWC ] (last visited Apr. 30, 2022).

On the research challenges of extracting rules from statutory texts, see Ashley , supra note 5, at 259–84 (Chapter 9 entitled “Extracting Information from Statutory and Regulatory Texts”).

Vanessa Mai, Caterina Neef & Anja Richert, " Clicking vs. Writing"—The Impact of a Chatbot’s Interaction Method on the Working Alliance in AI-based Coaching , Coaching | Theorie & Praxis § 5.2 (Jan. 14, 2022), https://link.springer.com/article/10.1365/s40896-021-00063-3 [ https://perma.cc/M7SJ-CNW8 ].

See Richard Zorza, The Access to Justice “Sorting Hat”: Towards a System of Triage and Intake that Maximizes Access and Outcomes, 89 Denv. U. L. Rev. 859, 878–79 (2011) (describing how technology could assist in obtaining information from a client).

Depending on the answers, the expert system would pursue particular claims. For instance, in the early 1980s, an expert system on product liability posed questions and provided answer options like these:

Was the victim either the user or purchaser of the product? (Yes / No)

What was the status of the product when it was sold by the defendant? (Defective / Non-defective)

Was the product modified after manufacture by parties other than the defendant? (Yes / No)

Was the nature of the use of the product foreseeable? (Yes / No)

What is the legal status of the victim? (Adult / Minor)

Did the victim know the product was defective before he used it? (Yes / No)

Did the victim continue using the product, even after he found it defective? (Yes / No)

Did the victim have a means for protecting himself from the dangers of using the product? (Yes / No)

Did the victim use this means to protect himself? (Yes / No)

Did the victim know and appreciate the danger involved in the use of the product? (Yes / No)

What were the medical expenses of the plaintiff? $6,000

Donald A. Waterman & Mark A. Peterson, Models of Legal Decisionmaking: Research Design and Methods 45–46 (1981), https://www.rand.org/pubs/reports/R2717.html [ https://perma.cc/9QF7-TDJL ]. One can readily imagine expanding the questions with branches to cover related claims for negligence, causing injury to a third party, or injury to property or pain and suffering.

For a recent example of an online expert system that allows a user to navigate through complex legal options involving international family law, see Dimyadi et al., supra note 18, at 107–09.

The expert system in Waterman & Peterson , supra note 23, at 16, had rules to determine which of four states’ product liability law applied. Similarly, a triage component of the expert system in Dimyadi et al., supra note 18, at 107–09 had rules to resolve which international family law conventions applied.

Callister, supra note 1, at 187.

Id. at 170, 172, 195. Casetext, https://casetext.com/v2/ [ https://perma.cc/W6RR-M85L ] (last visited May 23, 2022).

Our attempts to conduct a similar search with With Lexis+ failed. On May 24, 2022, we cut and pasted the hypothetical of Figure 1 into the search box of Lexis+, having selected Illinois as the jurisdiction. The program retrieved no cases or statutes. Presumably, the input was too long.

Soha Khazaeli, Janardhana Punuru, Chad Morris, Sanjay Sharma, Bert Staub, Michael Cole, Sunny Chiu-Webster & Dhruv Sakalley, A Free Format Legal Question Answering System , in Proceedings of the Natural Legal Language Processing Workshop 107, 108–10 (2021).

Thomson Reuters Enterprise Centre GmbH v. ROSS Intelligence Inc., 529 F. Supp. 3d 303 (D. Del. 2021). See Press Release, ROSS Intelligence, ROSS Intelligence Says Allegations of Copyright Theft Are False, Motivated by Fear of Competition (May 7, 2020), https://blog.rossintelligence.com/post/westlaw-copyright-allegations-are-false [ https://perma.cc/H3QF-UGXH ]. As of February 7, 2022, the litigation is still dealing with document discovery and motions to dismiss claims. See Julie Sobowale, Digging In: The ROSS Antitrust Saga Against Westlaw Continues , CBA/ABC National ( Feb. 7, 2022), https://www.nationalmagazine.ca/en-ca/articles/legal-market/legal-tech/2022/digging-in [ https://perma.cc/SL7X-KHAG ].

Remus & Levy, supra note 9, at 503. Thomson Reuters offers a legal question answering service connected with Westlaw Edge called WestSearch Plus. Lexis Nexis offers Lexis Answers. See infra notes 66–67 and accompanying text.

ROSS Intelligence , supra note 8; see also Remus & Levy, supra note 9, at 503.

See Remus & Levy, supra note 9, at 503 & n.4.

Profile of ROSS Intelligence , Forbes , https://www.forbes.com/profile/ross-intelligence/?sh=10ed81c71e85 [ https://perma.cc/32ZE-2SFUf ] (last visited Apr. 30, 2022).

See Remus & Levy, supra note 9, at 523.

Ruben Kruiper, Ioannis Konstas, Alasdair Gray, Farhad Sadeghineko, Richard Watson & Bimal Kumar, SPaR.txt, A Cheap Shallow Parsing Approach for Regulatory Texts , arXiv (Oct. 4, 2021), https://arxiv.org/pdf/2110.01295.pdf [ https://perma.cc/Q8SS-TPW4 ].

Stanford Parser , http://nlp.stanford.edu:8080/parser/index.jsp [ https://perma.cc/YBN6-MAJE ] (last visited Apr. 30, 2022).

Jaromir Savelka, Vern R. Walker, Matthias Grabmair & Kevin D. Ashley, Sentence Boundary Detection in Adjudicatory Decisions in the United States , 58 Traitement Automatique des Langues, no. 2, at 21, 22 (2017).

See, e.g., Alan Buabuchachart, Katherine Metcalf, Nina Charness & Leora Morgenstern, Classification of Regulatory Paragraphs by Discourse Structure, Reference Structure, and Regulation Type , in 259 Frontiers in Artificial Intelligence and Applications: Legal Knowledge and Information Systems , 59, 59–62 (Kevin D. Ashley ed., 2013).

See generally Ashley , supra note 3, at 259–84 (Chapter 9 entitled “Extracting Information from Statutory and Regulatory Texts”).

Jiansong Zhang & Nora M. El-Gohary, Automated Information Transformation for Automated Regulatory Compliance Checking in Construction , 29 J. Computing in Civ. Eng’g, no. 4 (2015); Travis D. Breaux & David G. Gordon, Regulatory Requirements as Open Systems: Structures, Patterns and Metrics for the Design of Formal Requirements Specifications, Carnegie Mellon University Technical Report CMU-ISR-11-100 (2011); Travis D. Breaux & David G. Gordon, Regulatory Requirements Traceability and Analysis Using Semi-Formal Specifications, in International Working Conference on Requirements Engineering: Foundation for Software Quality, RESFQ 2013: Requirements Engineering: Foundation for Software Equality 141, 157 (2013).

See, e.g. , Kenji Takano, Makoto Nakamura, Yoshiko Oyama & Akira Shimazu, Semantic Analysis of Paragraphs Consisting of Multiple Sentences Towards Development of a Logical Formulation System, 223 Frontiers in Artificial Intelligence and Applications: Legal Knowledge and Information Systems 117, 119–20 (2010); Ngo Xuan Bach, Nguyen Le Minh, Tran Thi Oanh & Akira Shimazu, A Two-Phase Framework for Learning Logical Structures of Paragraphs in Legal Articles, 12 ACM Transactions on Asian Language Info. Processing (TALIP) , no. 1, article 3, 2–3 (2013).

See Zhang & El-Gohary, supra note 42.

Layman E. Allen & C. Rudy Engholm, Normalized Legal Drafting and the Query Method , 29 J. Legal Educ. 380, 402–04 (1977); Layman E. Allen & Charles S. Saxon, Some Problems in Designing Expert Systems to Aid Legal Reasoning, in Proceedings of the First International Conference on Artificial Intelligence & Law 94 (1987); see also Ashley , supra note 3, at 40–44.

Current efforts to develop “computable” statutes need to resolve syntactic ambiguities inherent in statutory texts. See, e.g., Tom Barraclough, Hamish Fraser & Curtis Barnes, Legislation as Code for New Zealand (Mar. 2021), http://www.nzlii.org/nz/journals/NZLFRRp/2021/3.html [ https://perma.cc/7BCP-DYAP ].

See, e.g. , Dimyadi et al., supra note 18, at 116.

Lexis Answers on Lexis+ , http://lexisnexis.custhelp.com/app/answers/answer_view/a_id/1098212/~/lexis-answers-on-lexis-advance [ https://perma.cc/FH2K-9E2Q ] (last visited Apr. 30, 2022); Callister, supra note 1, at 200.

Lexis Answers on Lexis+, supra note 48.

NLP-progress , http://nlpprogress.com/english/natural_language_inference.html [ https://perma.cc/YPU7-R4UN ] (last visited Apr. 30, 2022).

Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy & Samuel R. Bowman, GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding, arXiv (Feb. 22, 2019), https://arxiv.org/pdf/1804.07461.pdf [ https://perma.cc/HXG7-6G4U ].

Mi-Young Kim & Randy Goebel, Two-Step Cascaded Textual Entailment for Legal Bar Exam Question Answering, in Proceedings of the 16 th edition of the International Conference on Artificial Intelligence & Law 283, 283–84 (2017); see also Mi-Young Kim, Juliano Rabelo & Randy Goebel, Statute Law Information Retrieval and Entailment, in Proceedings of the Seventeenth International Conference on Artificial Intelligence & Law 283, 283–84 (2019). One sample question asks, “Is it true that a special provision that releases warranty can be made, but in that situation, when there are rights that the seller establishes on his/her own for a third party, the seller is not released of warranty?” Kim & Goebel, supra , at 283. Another sample question states, “In cases an agent is entrusted to perform any specific juristic act, if the agent performs such act in accordance with the instructions of the principal, the principal may not assert that the agent did not know a particular circumstance without negligence which the principal did not know due to his/her negligence.” Kim, Rabelo & Goebel, supra , at 287.

Kim & Goebel, supra note 52, at 285–88; Kim, Rabelo & Goebel, supra note 52, at 285–86.

Anne Gardner, An Artificial Intelligence Approach to Legal Reasoning 160–67 (1987). As elaborated in Edwina Rissland, Artificial Intelligence and Law: Stepping Stones to a Model of Legal Reasoning, 99 Yale L.J. 1957, 1969 (1990), Gardner developed heuristics for deciding whether, given a fact situation, the applicability of term in a legal rule presented a hard or easy question of law. These heuristics depended on whether the term had an applicable commonsense definition and whether there were relevant examples or counterexamples of the term’s application. Id . at 1970. The method was heuristic in that it was not guaranteed to work, but it often did work. Id . at 1966. The approach was elegant because it was not computationally as expensive as always attempting to generate arguments regarding all potentially applicable terms in a legal rule. Id . at 1970.

An important exception is Thorne McCarty’s classic work on TaxmanII. L Thorne McCarty & Natesa Sridharan, The Representation of an Evolving System of Legal Concepts: II. Prototypes and Deformations , in 1 Proceedings of the 7 th International Joint Conference on Artificial Intelligence 246 (1981). It employed a logical representation of the meaning of a small set of legal concepts involving corporate tax and employed prototypes and deformations to identify case-based and example-based arguments about their meaning, but it was limited in its scope and realization to modeling one U.S. Supreme Court case. L. Thorne McCarty, An Implementation of Eisner v. Macomber, in Proceedings of the 5 th International Conference on Artificial Intelligence and Law 276, 277-79 (1995). Its analysis began with a manually inputted representation of cases or hypotheticals based on a human’s reading of the text; the program did not analyze the texts itself.

See, e.g. , Karl Branting, Building Explanations from Rules and Structured Cases, 34 Int’l J. Man-Machine Stud . 797 (1991); Kevin Ashley & Stefanie Brüninghaus, Computer Models for Legal Prediction, 46 Jurimetrics J. 309 (2006); Edwina Rissland & David Skalak, CABARET: Statutory Interpretation in a Hybrid Architecture, 34 Int’l J. Man-Machine Stud. 839 (1991); Matthias Grabmair & Kevin Ashley, Facilitating Case Comparison Using Value Judgments and Intermediate Legal Concepts , in Proceedings of the Thirteenth International Conference on Artificial Intelligence and Law 161 (2011).

Branting, supra note 56.

Kevin D. Ashley, Reasoning with Cases and Hypotheticals in HYPO , 34 Int’l J. Man-Machine Stud . 753, 757, 761 (1991).

Vincent Aleven, Using Background Knowledge in Case-Based Legal Reasoning: A Computational Model and an Intelligent Learning Environment, 150 Artificial Intelligence 183 (2003).

Rissland & Skalak, supra note 56.

Ashley & Brüninghaus, supra note 56.

Grabmair & Ashley, supra note 56.

Branting, supra note 56 at 800.

Susan Nevelow Mart, et al., Inside the Black Box of Search Algorithms, AALL Spectrum , Nov.-Dec. 2019, at 10, https://scholar.law.colorado.edu/articles/1238/ [ https://perma.cc/2DHX-E6Y5 ] (last visited Apr. 30, 2022).

Tonya Custis, et al., Westlaw Edge AI Features Demo: KeyCite Overruling Risk, Litigation Analytics, and WestSearch Plus , in Proceedings of the Seventeenth International Conference on Artificial Intelligence and Law 256 (2019). Mart et al., supra note 66, at 14.

Two AI and Law projects came close to this goal; both modeled legal argument as theory construction. Thorne McCarty’s program aimed at constructing competing rule-like theories induced from two decided cases and one agreed-upon hypothetical justifying an argued-for outcome in one new case. See McCarty & Sridharan, supra note 55. Chorley’s and Bench-Capon’s AGATHA program induced rules embodying preferences among competing factors and values and used them to construct theory-based arguments on how to resolve a new case. Alison Chorley & Trevor Bench-Capon, AGATHA: Using Heuristic Search to Automate the Construction of Case Law Theories , 13 Artificial Intelligence & L. 9 (2005); Alison Chorley & Trevor Bench-Capon, An Empirical Investigation of Reasoning with Legal Cases Through Theory Construction and Application , 13 Artificial Intelligence & L. 323 (2005).

An account of a systematic effort to identify factors in landlord-tenant decisions and of the challenges of extracting them automatically may be found in Hannes Westermann, Vern R. Walker, Kevin D. Ashley & Karim Benyekhlef, Using Factors to Predict and Analyze Landlord-Tenant Decisions to Increase Access to Justice , in Proceedings of the Seventeenth International Conference on Artificial Intelligence and Law 133 (2019).

Karl Branting, Craig Pfeifer, Bradford Brown, Lisa Ferro, John Aberdeen, Brandy Weiss, Mark Pfaff & Bill Liao, Scalable and Explainable Legal Prediction , 29 Artificial Intelligence & L. 213 (2021).

Id. at 232–35. WIPO’s Arbitration and Mediation Center provides rules and mechanisms to resolve internet domain name disputes, without the need for litigation in court. https://www.wipo.int/amc/en/center/index.html [ https://perma.cc/C9FG-S6RZ ] (last visited May 22, 2022).

Mohammad H. Falakmasir & Kevin D. Ashley, Utilizing Vector Space Models for Identifying Legal Factors from Text , in 302 Frontiers in Artificial Intelligence and Applications: Legal Knowledge and Information Systems 183 (Adam Wyner & Giovanni Casini eds., 2017).

For a detailed account of how this might be accomplished, see Ashley , supra note 3, at 350–92 (Chapter 12 entitled “Cognitive Computing Legal Apps”).

See, e.g. , Nikolaos Aletras, Dimitrios Tsarapatsanis, Daniel Preoţiuc-Pietro & Vasileios Lampos, Predicting Judicial Decisions of the European Court of Human Rights: A Natural Language Processing Perspective , 2 PeerJ Computer Science e93 (2016). Masha Medvedeva, Michel Vols & Martijn Wieling, Using Machine Learning to Predict Decisions of the European Court of Human Rights , 28 Artificial Intelligence & L. 237 (2020).

See Heung-Il Suk, An Introduction to Neural Networks and Deep Learning , in Deep Learning for Medical Image Analysis 3 (2017).

Ilias Chalkidis, Ion Androutsopoulos & Nikolaos Aletras. Neural Legal Judgment Prediction in English , arXiv (J une 5, 2019), https://arxiv.org/pdf/1906.02059.pdf [ https://perma.cc/8FY6-AQVY ].

Zhou, supra note 5 at 4.

For a brief description of neural networks, see Suk, supra note 76.

Chalkidis et al., supra note 78.

Heet Sankesara, Hierarchical Attention Networks, Analytics Vihya (Aug. 23, 2018), https://medium.com/analytics-vidhya/hierarchical-attention-networks-d220318cf87e [ https://perma.cc/TKS8-SRX5 ].

Karl Branting, Brandy Weiss, Bradford Brown, Craig Pfeifer, A. Chakraborty, Lisa Ferro, Mark Pfaff & Alexander Yeh, Semi-Supervised Methods for Explainable Legal Prediction , in Proceedings of the Seventeenth International Conference on Artificial Intelligence and Law 22 (2019).

Branting et al. , supra note 69.

Branting et al., supra note 87.

Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei & Ilya Sutskever, Language Models Are Unsupervised Multitask Learners (2019), https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf [ https://perma.cc/U5KU-2YV7 ].

John Pavlus, Machines Beat Humans on a Reading Test. But Do They Understand? , Quanta Magazine (Oct. 17, 2019), https://www.quantamagazine.org/machines-beat-humans-on-a-reading-test-but-do-they-understand-20191017/ [ https://perma.cc/YFW2-DEKU ].

Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan et al., Language Models Are Few-Shot Learners , arXiv ( July 22, 2020), https://arxiv.org/pdf/2005.14165.pdf [ https://perma.cc/T4ND-5QG7 ].

Pavlus, supra note 91.

Brown et al., supra note 95.

Radford et al., supra note 90.

Talk to Transformer, https://talktotransformer.com/ (now called InferKit, https://inferkit.com/ ) [ https://perma.cc/XE4H-Z5GB ] (last visited Apr. 30, 2022). See Kelsey Piper, An AI Helped Us Write This Article , Vox (Feb. 14, 2019, 12:50 PM), https://www.vox.com/future-perfect/2019/2/14/18222270/artificial-intelligence-open-ai-natural-language-processing [ https://perma.cc/F9AT-LBMW ].

As illustrated in Figure 9 , GPT-2 and its successor, GPT-3 often leave sentences unfinished. See, e.g., Miguel Grinberg, The Ultimate Guide to OpenAI’s GPT-3 Language Model , https://www.twilio.com/blog/ultimate-guide-openai-gpt-3-language-model [ https://perma.cc/CM32-D9XC ] (last visited May 22, 2022).

See, e.g. , Illinois Pattern Jury Instructions-Civil § 30.04.01 Measure of Damages—Disability/Loss of a Normal Life (citing Smith v. City of Evanston, 631 N.E.2d 1269 (Ill. App. Ct. 1994) (“Loss of a normal life is recognized as a separate element of compensable damages in Illinois.”).

Dog Bites , Brabender Law LLC , https://bc-firm.com/chicago-dog-bite-lawyer/ [ https://perma.cc/8P3P-UGT2 ] (last visited Apr. 30, 2022). The term is also used on the website of Law Offices of John J. Malm & Associates. Illinois Dog Bite Injuries , Law Offices of John J. Malm & Associates , https://www.malmlegal.com/illinois-dog-bite-injuries.html [ https://perma.cc/M6ZC-EYLZ ] (last visited Apr. 30, 2022). While a Google search did not find a Jason A. Bendoff, an attorney named Bendoff is mentioned on the Malm & Associates website.

Tony Zhao, Eric Wallace, Shi Feng, Dan Klein & Sameer Singh, Calibrate Before Use: Improving Few-Shot Performance of Language Models , arXiv ( June 10, 2021), https://arxiv.org/pdf/2102.09690.pdf [ https://perma.cc/PV77-77ZR ].

Casetext, https://casetext.com/v2/ [ https://perma.cc/W6RR-M85L ] (last visited May 24, 2022).

Westlaw Edge Quick Check, https://1.next.westlaw.com/QuickCheck?transitionType=Default&contextData=(sc.Default) (last visited May 24, 2022).

Lexis+ Brief Analysis

https://plus.lexis.com/briefAnalysis?crid=82c5aa19-6510-49f2-9aec-cc1ffad70cad#/briefAnalysis/singleBrief (last visited May 24, 2022). Fastcase Cloud Linking

In an uploaded brief or memo, Fastcase Cloud Linking augments case citations with publicly available hyperlinks to the cited cases. It does not appear to analyze the text, however. Fastcase Cloud Linking, https://fc7.fastcase.com/ (last visited May 24, 2022).

Hudgins, supra note 11.

For example, LEGAL-BERT is a language model pre-trained on a corpus including legal documents. It improved performance on a number of tasks. Ilias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis, Nikolaos Aletras & Ion Androutsopoulos, LEGAL-BERT: The Muppets Straight Out of Law School , arXiv ( Oct. 6, 2020), https://arxiv.org/pdf/2010.02559.pdf [ https://perma.cc/UD9W-X29V ].

Lazar Peric, Stefan Mijic, Dominik Stammbach & Elliott Ash, Legal Language Modeling with Transformers , Proceedings of ASAIL (2020), http://ceur-ws.org/Vol-2764/paper2.pdf [ https://perma.cc/89DP-FSAZ ].

Karen Hao, AI Still Doesn’t Have the Common Sense to Understand Human Language , MIT Tech. Rev. (Jan. 31, 2020), https://www.technologyreview.com/s/615126/ai-common-sense-reads-human-language-ai2/ [ https://perma.cc/H9Q4-ZD8Q ].

Peric et al., supra note 111, at 6, 8.

According to David Ferrucci, the leader of IBM’s team that developed Watson, transformer models like GPT-3 are “super-parrots.” “They do well at narrow tasks, but only by constantly asking themselves one simple question: ‘Based on all the documents I’ve seen, what would a human likely say here?’ . . . What’s left unwritten . . . is the vast body of shared experience that led humans to write the words in the first place.” David Ferrucci, Can Super-Parrots Ever Achieve Language Understanding? , Elemental Cognition (May 21, 2020),

https://medium.com/@ElementalCognition/can-super-parrots-ever-achieve-language-understanding-8307dfd3e87c [ https://perma.cc/C64D-S6E7 ]. Presumably, much of the common sense shared experience of legal practice is also unwritten and inaccessible to transformer models. GPT-3 can generate realistic appearing answers with little training, but one cannot yet rely on their legal correctness.

Gary Marcus & Ernest Davis, Rebooting AI: Building Artificial Intelligence We Can Trust (2019), adapted in Gary Marcus & Ernest Davis, If Computers Are So Smart, How Come They Can’t Read? , Wired . (Sep. 10, 2019), https://www.wired.com/story/adaptation-if-computers-are-so-smart-how-come-they-cant-read/ [ https://perma.cc/9MH3-N56P ].

See Jeremy Paul, Changing the Subject: Cognitive Theory and the Teaching of Law , 67 Brook. L. Rev . 987, 1006, 1008, 1022 (2002).

Supra Part 2.

Jaromir Savelka, Matthias Grabmair & Kevin D. Ashley, A Law School Course in Applied Legal Analytics and AI , 37 Law in Context 134 (2020).

The excerpts are from Teresa Kissane Brostoff & Ann Sinsheimer , United States Legal Language and Culture: An Introduction to the U.S. Common Law System (3d ed. 2013).

What are you writing about today?

Write better essays, in less time, with your ai writing assistant.

Filter by Keywords

10 Legal AI Tools for Legal Practices and Professionals in 2024

Senior Content Marketing Manager

February 13, 2024

Ever spent a late night reading a much-too-long legal document? In the legal industry, you’ve probably had a lot of those nights. 

Fortunately, artificial intelligence (AI) is here to help with that. 🙌

While some of the top legal AI tools are apps designed to summarize or draft legal documents, that’s not the only use case for AI in the legal industry. There are legal research tools, software to help law firms manage casework, apps designed to draft contracts, and more. 

Let’s make life in the legal world easier. Explore the 10 best AI tools for lawyers.

What Are AI Tools for Lawyers?

What should you look for in ai tools for lawyers, 4. detangle.ai, 5. ansarada, 6. lex machina, 8. ai lawyer, 9. patentpal, 10. humata ai.

AI legal assistant tools aren’t chatbots that can argue your cases for you. They are helpful tools that can do a lot to streamline your day-to-day tasks. Many of these tools will help you draft complex legal documents and contracts, while others provide simplified summaries to read abridged versions of lengthy legal documents. 

Examples of AI tools for lawyers include workflow optimization apps, calendar and planner apps , and research tools. The one thing most have in common is that they typically rely on a language model like ChatGPT to help you get work done faster.

Finding a great app or tool comes down to discovering one with all the features you need—and for a law firm, paralegals, and other corporate legal departments, that isn’t always an easy feat. The best apps for your legal practice should provide all of the following:

• Affordable pricing: OpenAI doesn’t charge much to use ChatGPT 4.0, which means you shouldn’t pay excessively for basic AI features—though some AI tools for lawyers offer additional features that are worth the cost
• Document management: Apps should make it easy to upload, attach, and share Word files, PDFs, and other file types 📚
• Collaboration features: Keep law firms and clients in the know with the ability to collaborate and comment on files
• Access permissions: Most legal documents are confidential, which means that you should be able to set permissions and control who accesses the app and the documents you’ve uploaded to it
• Free and trial options: Since some AI tools for lawyers can be on the pricey side, make sure that you can try it before you buy it

The 10 Best AI Tools for Lawyers to Use in 2024

With the fast popularity of ChatGPT, chatbots, and artificial intelligence in general, there are tons of new AI legal assistant tools out there. We’ve done the hard work of sifting through providers to bring you the best new tech options to help legal professionals work more efficiently.

ClickUp has a lot to offer in the way of legal solutions. As an all-in-one productivity platform, it’s the ideal software to help legal professionals centralize all of their work into one dynamic Workspace. With over 15 customizable views, you can visualize your caseload from every angle including List, Calendar, and Table view. You can also create custom Dashboards for real-time analytics and reports on various processes while maintaining a high-level overview of important tasks. 

Plus, native time tracking, tags, and billable hours features in ClickUp are critical for keeping track of time spent with clients and creating accurate invoices. Assigned comments are also a major asset for lawyers communicating with their peers and clients within ClickUp. With the power to add PDFs, media, and other files to each comment, lawyers can ensure all key information stays with its corresponding task throughout the case. And to get started even quicker in ClickUp, try the ready-made Legal Client Management Template to stay organized.

However, ClickUp’s most valuable feature for lawyers, hands down, is ClickUp Brain —the revolutionary AI-powered digital assistant with contextual, role-based AI features. ClickUp Brain uses natural language processing to generate emails, documents, tasks, summaries, and updates. What’s more, while ClickUp Brain is handling the heavy lifting of your caseload, Automations in ClickUp can pick up the rest. From summarizing legal research to automatically generating new tasks throughout your process, ClickUp has every feature legal professionals need to stay on top of every case.

Bonus: Access pre-built AI templates with ChatGPT prompts to merge the power of ClickUp Brain with other machine-learning tools.

ClickUp best features:

• Use ClickUp Brain to draft complex legal documents, create emails, generate status reports, and more
• Use project management features to track cases, schedule meetings , and optimize your legal team’s workflow
• Time tracking and billable hours to help legal professionals invoice clients and create timesheets
• Communicate and collaborate via commenting features and shared documents
• Use ClickUp Brain to summarize legal research and automate repetitive tasks like emails, memos, document summaries, and more

ClickUp limitations:

• Not all views are available in the mobile app yet
• Tons of powerful features can pose a bit of a learning curve for newer users

ClickUp pricing:

• Free Forever
• Unlimited: $7/month per user
• Business: $12/month per user
• Enterprise: Contact for pricing
• ClickUp Brain is available on all paid plans for $5 per Workspace member per month

ClickUp ratings and reviews:

• G2: 4.7/5 (8,900+ reviews)
• Capterra: 4.6/5 (3,800+ reviews)

Lawgeex is what you need if you want to automate the contract review process. The app uses AI-driven tools to review and redline contracts in accordance with your company’s policies, guidelines, and other legal concepts. With this tool, legal teams can create consistency across contracts, save tons of time and money on the review process, and close deals faster.

Lawgeex best features:

• Save time on high-volume contract analysis for non-disclosures, service agreements, and more
• Use integrations with popular customer relationship management systems and other apps
• Use integrations or email to submit other legal documents for automatic redlining
• Create a custom playbook of contract review guidelines specific to your law firm
• Track reviews, types of legal issues most frequently redlined, and other details with analytics

Lawgeex limitations:

• Not yet enough user feedback to provide insights
• May not be ideal for high-value contract management

Lawgeex pricing:

• Pricing may vary—contact Lawgeex for details

Lawgeex ratings and reviews:

• Capterra: N/A

Amto relies on generative artificial intelligence to help you draft contracts, emails, letters, templates, and more. Law firms and various legal professionals use it to create service agreement templates, work-for-hire contracts, arbitration, real estate contracts, and other types of agreements—all in a uniform, concise tone that can be tailored to suit individual clients.

Amto best features:

• Use generative AI based on ChatGPT for drafting legal documents, letters, and emails
• Highlight sections of text and enter instructions for instant revisions
• Get recommendations for missing clauses, gaps in legal research, or language in legal documents
• Create reminders for clients concerning deadlines and other important dates

Amto limitations:

• Monthly fees are high, given word count and feature limitations
• Not recommended for complex or high-value legal documents

Amto pricing:

• Basic: Draft for free, $99/month for access to most features
• Professional: Additional words and features for $499/month
• Custom: Flexible pricing based on your needs

Amto ratings and reviews:

Detangle makes innovative use of AI technology for summarizing lengthy legal research or transforming complex jargon into plain English. With this app, you can upload audio, video, or text, and the app automatically summarizes it. ✨

Detangle.ai best features:

• Upload assets or paste URLs in a simple interface
• Get AI-generated summaries of lengthy documents, audio files, or video
• Simplify complex legal jargon
• Pay per summary rather than a monthly fee

Detangle.ai limitations:

• May need to join a new user waitlist before you can use the app
• Per-file fees are expensive, even for shorter documents

Detangle.ai pricing:

• Varies by document, audio, or video length

Detangle.ai ratings and reviews:

Ansarada isn’t necessarily a legal platform—but it is a platform that enterprises and their legal teams rely on to manage workflows and collaborate on critical tasks like deals, mergers and acquisitions, regulatory compliance, and so on. With secure file-sharing, dashboards, notifications, and other features, enterprises also use Ansarada to organize governance, risk, and compliance policies; for procurement management; and to unify processes.

Ansarada best features:

• Organize deals with AI-powered data rooms
• Create customizable, purpose-built workflows for high-stakes deals
• Get visibility into activity information to make informed decisions during deals
• AI tools often accurately predict merger and bidding outcomes

Ansarada limitations:

• Deleting users or documents also deletes associated audit trails
• Uploading or handling large batches of files can lead to lags
• Navigating the app may be challenging for new users

Ansarada pricing:

• $399/month for 250MB data package
• $1,231/month for 1GB data package
• $1,702/month for 2GB data package
• $2,351/month for 4GB data package
• Custom pricing over 4GB

Ansarada ratings and reviews:

• G2: 4.5/5 (125+ reviews)
• Capterra: 4.7/5 (100+ reviews)

Lex Machina is a cutting-edge AI-powered tool that can handle a lot of legal research for you. It’s an analytics platform that lets you analyze courts, judges, opposing counsel, various parties, and even law firms. Because this app offers easy access to court dockets, you can also use it to find relevant case law. Legal firms use this research to close deals, craft successful strategies, and win cases. 👀

Lex Machina best features:

• Generate comprehensive reports showing damages awarded, case statistics, and other vital metrics
• Use Legal Analytics Quick Tools to compare judges, law firms, parties, and more
• Use Lex Machina’s application programming interface (API) to create your own custom applications
• Access documents from court dockets directly within the app

Lex Machina limitations:

• Lex Machina isn’t self-service—you’ll need to work with their sales team to sign up and choose the tools you need
• Few reviews exist to provide insights for new users

Lex Machina pricing:

• Pricing varies based on the services selected

Lex Machina ratings and reviews:

• Capterra: 2/5 (1 rating)

Using Latch is like merging your AI legal assistants inside MS Word. Once you’ve integrated it with Word, you can use it for general case management or treat it as your personal AI-powered contract review tool. This document analysis tool generates redline suggestions, modifies clauses, and determines if clauses are up to market standards. It will also help you summarize agreements and generate simplified language to assist readers who don’t have a legal background.

Latch best features:

• Integrate directly into Microsoft Word in a few simple steps
• Use Track Changes to automatically insert AI-generated changes into your document
• Create custom instructions to modify language throughout
• Use custom requirements to ensure that contracts meet specific conditions
• Integrate with popular cloud storage to easily share and collaborate on documents

Latch limitations:

• Only works with Word—there’s no support for Google Docs or other popular word processing apps
• Latch isn’t self-service—you’ll need to request access and sign up for partial access, then work with Latch’s team for full access to the tools

Latch pricing:

• Contact Latch’s sales team to learn more

Latch ratings and reviews:

AI Lawyer is an innovative tool made with everyone in mind. For general audiences, it can provide legal information and simplify legal language. Lawyers use this tool for legal research and to brainstorm strategies, and law students can use AI Lawyer to hone their legal research skills and to get insights into modern legal trends.

AI Lawyer best features:

• Get fast, easy-to-understand insights into complex legal issues
• Upload documents to get a simplified summary
• Create simple legal agreements in just minutes
• Streamlines legal research and provides suggestions for legal strategies

AI Lawyer limitations:

• While it can create simple legal documents, it may not be suited for creating complex documents
• Be prepared for a learning curve—some features can be confusing or hard to find

AI Lawyer pricing:

• Just Ask: $9.99/week
• Golden Choice: Try for free, then $19.99/month
• Big Case: $99.99/year

AI Lawyer ratings and reviews:

PatentPal is a document automation tool that relies on natural language processing to generate documentation for your intellectual property. Legal practices and creators alike can use this app for patent applications, flow charts, diagrams, and everything else needed to file a patent claim. While you may want a legal expert to review your finished application, this app takes a lot of the back and forth—and time and effort—out of the application drafting process.

PatentPal best features:

• Use templates to create patent applications and other documentation
• Create figures, diagrams, and flow charts to support claims 
• Upload illustrations and customize them with labels
• Export your drafts into Word, Visio, or PowerPoint

PatentPal limitations:

• The app only creates content based on what claims provide, which means you’ll need to be accurate and thorough in your claims
• There is a small learning curve when you’re figuring out how best to phrase claims to get the best outputs

PatentPal pricing:

• Sign up for a free trial to learn more about costs

PatentPal ratings and reviews:

With Humata, you can upload documents to simplify technical papers, legal information, and more. It gives you options for creating summaries of different lengths—simply ask the app to shorten a lengthy summary if needed. It also offers a feature for citations. Click a citation within a summary, and the app will show you the relevant information from the uploaded document.

Humata AI best features:

• Use citations from your summaries to trace legal research from the documents you’ve uploaded
• Revise and refine summaries with simple commands
• Embed Humata into your web pages so customers can use it like a search engine to find answers
• Use Humata’s secure private cloud to share files and collaborate
• Control access to files by setting up team roles with limited privileges

Humata AI limitations:

• There’s a cost of $0.01 per page for each page over your plan’s limit
• Since it’s made specifically for technical and legal documents, it may not summarize other types of documents as well

Humata AI pricing:

• Free: Summarize up to 60 pages free
• Student: $1.99/month to summarize up to 200 pages
• Expert: $9.99/month to summarize up to 500 pages
• Team: $99/month to summarize up to 1,000 pages

Humata AI ratings and reviews:

Streamline practice management with the best ai tools for lawyers.

Artificial intelligence is taking the world by storm—and that includes the legal industry. With the right AI legal assistant tool, you can cut time-consuming tasks from your schedule, get help with document reviews, and even get advanced assistance, like finding relevant precedents or other legal services. 🙌

Ready to let AI handle a few of your legal tasks? Get started with ClickUp to discover how it can help you manage your legal practice efficiently.

Questions? Comments? Visit our Help Center for support.

Receive the latest WriteClick Newsletter updates.

Thanks for subscribing to our blog!

Please enter a valid email

• Free training & 24-hour support
• Serious about security & privacy
• 99.99% uptime the last 12 months

Create any essay

In seconds..

Unlock your full writing potential with our cutting-edge AI essay generation tool. Say goodbye to late nights and writer's block, and hello to effortless writing.

Charley is powered by Artificial Intelligence, and he's here to help.

It takes less than a minute, and it’s free

Let AI transform the way you write. Our 200,000+ users already have!

Charley AI will take you all the way from deciding on a topic, to submitting your essay in a matter of seconds.

Get Inspired

Charley identifies the ideal topics for your essay and provides insightful example essays to inspire and guide you.

Get Better Grades

Our AI adapts to your desired grade level, and will tailor it's writing style and word choice to suit the grade you want your essay be marked.

Intuitive Essay Generator

Experience seamless essay generation with our user-friendly text editor. Craft compelling essays effortlessly and unlock your full writing potential.

Customizable Essay Creation

Personalize your writing journey with our versatile essay creation page. Select the tone, essay type, word count, and desired grade to start writing the perfect essay tailored to your needs.

175,000+ Users Here's what they say:

I haven't written an essay in 4 months now, and i've got nothing but straight A's and B's. This website is crazy!

Melissa Smith

Michigan State Student

I have no idea how they do this, but it gets me good grades and that's all I care about.

Jake Johnson

Pine View Student

Just wrote my 4,000 word essay before my teacher finished presenting it... WTF!

Alfred Williams

Penn State Student

Essays Written

Support & Help

Plagiarism-free

Do You Have Any Questions? We have the answers.

Embrace effortless writing try our ai essay generator now.

AI improves legal writing speed, not quality - study

• Medium Text

• Company Microsoft Corp Follow

Sign up here.

Reporting by Karen Sloan

Our Standards: The Thomson Reuters Trust Principles. New Tab , opens new tab

Thomson Reuters

Karen Sloan reports on law firms, law schools, and the business of law. Reach her at [email protected]

Read Next / Editor's Picks

Industry Insight Chevron

Mike Scarcella, David Thomas

Karen Sloan

Henry Engler

Diana Novak Jones

Turn Your Curiosity Into Discovery

Latest facts.

11 Facts About National Love Your Produce Manager Day April 2nd

10 Facts About National Clean Out Your Medicine Cabinet Day April 19th

40 facts about elektrostal.

Written by Lanette Mayes

Modified & Updated: 02 Mar 2024

Reviewed by Jessica Corbett

Elektrostal is a vibrant city located in the Moscow Oblast region of Russia. With a rich history, stunning architecture, and a thriving community, Elektrostal is a city that has much to offer. Whether you are a history buff, nature enthusiast, or simply curious about different cultures, Elektrostal is sure to captivate you.

This article will provide you with 40 fascinating facts about Elektrostal, giving you a better understanding of why this city is worth exploring. From its origins as an industrial hub to its modern-day charm, we will delve into the various aspects that make Elektrostal a unique and must-visit destination.

So, join us as we uncover the hidden treasures of Elektrostal and discover what makes this city a true gem in the heart of Russia.

Key Takeaways:

• Elektrostal, known as the “Motor City of Russia,” is a vibrant and growing city with a rich industrial history, offering diverse cultural experiences and a strong commitment to environmental sustainability.
• With its convenient location near Moscow, Elektrostal provides a picturesque landscape, vibrant nightlife, and a range of recreational activities, making it an ideal destination for residents and visitors alike.

Known as the “Motor City of Russia.”

Elektrostal, a city located in the Moscow Oblast region of Russia, earned the nickname “Motor City” due to its significant involvement in the automotive industry.

Home to the Elektrostal Metallurgical Plant.

Elektrostal is renowned for its metallurgical plant, which has been producing high-quality steel and alloys since its establishment in 1916.

Boasts a rich industrial heritage.

Elektrostal has a long history of industrial development, contributing to the growth and progress of the region.

Founded in 1916.

The city of Elektrostal was founded in 1916 as a result of the construction of the Elektrostal Metallurgical Plant.

Located approximately 50 kilometers east of Moscow.

Elektrostal is situated in close proximity to the Russian capital, making it easily accessible for both residents and visitors.

Known for its vibrant cultural scene.

Elektrostal is home to several cultural institutions, including museums, theaters, and art galleries that showcase the city’s rich artistic heritage.

A popular destination for nature lovers.

Surrounded by picturesque landscapes and forests, Elektrostal offers ample opportunities for outdoor activities such as hiking, camping, and birdwatching.

Hosts the annual Elektrostal City Day celebrations.

Every year, Elektrostal organizes festive events and activities to celebrate its founding, bringing together residents and visitors in a spirit of unity and joy.

Has a population of approximately 160,000 people.

Elektrostal is home to a diverse and vibrant community of around 160,000 residents, contributing to its dynamic atmosphere.

Boasts excellent education facilities.

The city is known for its well-established educational institutions, providing quality education to students of all ages.

A center for scientific research and innovation.

Elektrostal serves as an important hub for scientific research, particularly in the fields of metallurgy, materials science, and engineering.

Surrounded by picturesque lakes.

The city is blessed with numerous beautiful lakes, offering scenic views and recreational opportunities for locals and visitors alike.

Well-connected transportation system.

Elektrostal benefits from an efficient transportation network, including highways, railways, and public transportation options, ensuring convenient travel within and beyond the city.

Famous for its traditional Russian cuisine.

Food enthusiasts can indulge in authentic Russian dishes at numerous restaurants and cafes scattered throughout Elektrostal.

Home to notable architectural landmarks.

Elektrostal boasts impressive architecture, including the Church of the Transfiguration of the Lord and the Elektrostal Palace of Culture.

Offers a wide range of recreational facilities.

Residents and visitors can enjoy various recreational activities, such as sports complexes, swimming pools, and fitness centers, enhancing the overall quality of life.

Provides a high standard of healthcare.

Elektrostal is equipped with modern medical facilities, ensuring residents have access to quality healthcare services.

Home to the Elektrostal History Museum.

The Elektrostal History Museum showcases the city’s fascinating past through exhibitions and displays.

A hub for sports enthusiasts.

Elektrostal is passionate about sports, with numerous stadiums, arenas, and sports clubs offering opportunities for athletes and spectators.

Celebrates diverse cultural festivals.

Throughout the year, Elektrostal hosts a variety of cultural festivals, celebrating different ethnicities, traditions, and art forms.

Electric power played a significant role in its early development.

Elektrostal owes its name and initial growth to the establishment of electric power stations and the utilization of electricity in the industrial sector.

Boasts a thriving economy.

The city’s strong industrial base, coupled with its strategic location near Moscow, has contributed to Elektrostal’s prosperous economic status.

Houses the Elektrostal Drama Theater.

The Elektrostal Drama Theater is a cultural centerpiece, attracting theater enthusiasts from far and wide.

Popular destination for winter sports.

Elektrostal’s proximity to ski resorts and winter sport facilities makes it a favorite destination for skiing, snowboarding, and other winter activities.

Promotes environmental sustainability.

Elektrostal prioritizes environmental protection and sustainability, implementing initiatives to reduce pollution and preserve natural resources.

Home to renowned educational institutions.

Elektrostal is known for its prestigious schools and universities, offering a wide range of academic programs to students.

Committed to cultural preservation.

The city values its cultural heritage and takes active steps to preserve and promote traditional customs, crafts, and arts.

Hosts an annual International Film Festival.

The Elektrostal International Film Festival attracts filmmakers and cinema enthusiasts from around the world, showcasing a diverse range of films.

Encourages entrepreneurship and innovation.

Elektrostal supports aspiring entrepreneurs and fosters a culture of innovation, providing opportunities for startups and business development.

Offers a range of housing options.

Elektrostal provides diverse housing options, including apartments, houses, and residential complexes, catering to different lifestyles and budgets.

Home to notable sports teams.

Elektrostal is proud of its sports legacy, with several successful sports teams competing at regional and national levels.

Boasts a vibrant nightlife scene.

Residents and visitors can enjoy a lively nightlife in Elektrostal, with numerous bars, clubs, and entertainment venues.

Promotes cultural exchange and international relations.

Elektrostal actively engages in international partnerships, cultural exchanges, and diplomatic collaborations to foster global connections.

Surrounded by beautiful nature reserves.

Nearby nature reserves, such as the Barybino Forest and Luchinskoye Lake, offer opportunities for nature enthusiasts to explore and appreciate the region’s biodiversity.

Commemorates historical events.

The city pays tribute to significant historical events through memorials, monuments, and exhibitions, ensuring the preservation of collective memory.

Promotes sports and youth development.

Elektrostal invests in sports infrastructure and programs to encourage youth participation, health, and physical fitness.

Hosts annual cultural and artistic festivals.

Throughout the year, Elektrostal celebrates its cultural diversity through festivals dedicated to music, dance, art, and theater.

Provides a picturesque landscape for photography enthusiasts.

The city’s scenic beauty, architectural landmarks, and natural surroundings make it a paradise for photographers.

Connects to Moscow via a direct train line.

The convenient train connection between Elektrostal and Moscow makes commuting between the two cities effortless.

A city with a bright future.

Elektrostal continues to grow and develop, aiming to become a model city in terms of infrastructure, sustainability, and quality of life for its residents.

In conclusion, Elektrostal is a fascinating city with a rich history and a vibrant present. From its origins as a center of steel production to its modern-day status as a hub for education and industry, Elektrostal has plenty to offer both residents and visitors. With its beautiful parks, cultural attractions, and proximity to Moscow, there is no shortage of things to see and do in this dynamic city. Whether you’re interested in exploring its historical landmarks, enjoying outdoor activities, or immersing yourself in the local culture, Elektrostal has something for everyone. So, next time you find yourself in the Moscow region, don’t miss the opportunity to discover the hidden gems of Elektrostal.

Q: What is the population of Elektrostal?

A: As of the latest data, the population of Elektrostal is approximately XXXX.

Q: How far is Elektrostal from Moscow?

A: Elektrostal is located approximately XX kilometers away from Moscow.

Q: Are there any famous landmarks in Elektrostal?

A: Yes, Elektrostal is home to several notable landmarks, including XXXX and XXXX.

Q: What industries are prominent in Elektrostal?

A: Elektrostal is known for its steel production industry and is also a center for engineering and manufacturing.

Q: Are there any universities or educational institutions in Elektrostal?

A: Yes, Elektrostal is home to XXXX University and several other educational institutions.

Q: What are some popular outdoor activities in Elektrostal?

A: Elektrostal offers several outdoor activities, such as hiking, cycling, and picnicking in its beautiful parks.

Q: Is Elektrostal well-connected in terms of transportation?

A: Yes, Elektrostal has good transportation links, including trains and buses, making it easily accessible from nearby cities.

Q: Are there any annual events or festivals in Elektrostal?

A: Yes, Elektrostal hosts various events and festivals throughout the year, including XXXX and XXXX.

Was this page helpful?

Our commitment to delivering trustworthy and engaging content is at the heart of what we do. Each fact on our site is contributed by real users like you, bringing a wealth of diverse insights and information. To ensure the highest standards of accuracy and reliability, our dedicated editors meticulously review each submission. This process guarantees that the facts we share are not only fascinating but also credible. Trust in our commitment to quality and authenticity as you explore and learn with us.

Share this Fact: