Transforming Legal Drafting With AI Assistance

AI isn’t replacing you. It’s sitting next to you. At Copenhagen Legal Tech’s First Tuesday, Werner Valeur shared so many great insights, but this one stuck with me: 🤖 Technology is your new colleague. I’d take it a step further: 🤖 AI is your new colleague. It’s not just another tech tool. Treat AI like a new coworker. Like any good colleague, AI requires context and interaction to deliver real value. The better you communicate with your new coworker - the better the results. The more you work together, the more you learn about their strengths and weaknesses. Laura Frederick helped further refine and visualize this concept yesterday while we were chatting about challenges of AI adoption in contracting. Use AI like you would when we worked in offices, and would drop by one of your office besties to run an idea by them, get a different opinion, refine argument or get a gut check. Here are some ways that you can use AI right now across all genAI chat tools like ChatGPT, Copilot, Claude, Gemini, Perplexity and legal specific AI tools like Wordsmith. How AI Can Assist Legal Professionals Right Now: 🧠 Brainstorming & Idea Generation - Generate new ideas and explore different perspectives. - Provide counterarguments to strengthen legal reasoning. - Get suggestions for alternative approaches to problems. 🤝 Negotiation & Scenario Testing - Play out different negotiation scenarios and refine your position. - Run hypotheticals or play devil’s advocate to stress-test legal arguments. 📑 Document & File Management - Spot differences between contract versions or precedent documents. - Organize messy notes into structured documents. - Structure messy drafts, clean up formatting, and standardize layouts. - Easily convert between file formats while maintaining all the information. 📝 Summarization & Transcription - Quickly extract key points from lengthy agreements or case law. - Transcribe and/or summarize meeting transcripts or notes to capture key takeaways and action items. 👀 Clarity & Refinement - Test writing for clarity and readability. - Ask AI to simplify or refine complex legal language. - Make writing more concise by cutting unnecessary details. - Turn text into bullet points, a table, or image (tip: Claude is better at making slide images). ⚠️ Risk & Consistency Checks - Highlight potential red flags in agreements. - Check for inconsistencies in responses or across multiple documents. - Ensure legal solutions align with specific legal rules, frameworks, or precedents. - Identify assumptions made in legal arguments. - Validate responses against the latest case law or regulatory updates. - Stress-test whether legal advice holds under different conditions. 🗣️ Client & Internal Communication - Tailor responses based on tone and audience. - Provide second opinions or alternative views on legal arguments or advice. - Prepare clear, concise explanations for clients or stakeholders. - My favorite: check for typos!

The next generation of document automation is here. And this time, I think it might actually change the adoption curve. For years, document automation has promised huge value for law firms, but rollout has often been painfully slow. Not because the value wasn’t there. Because the automation work itself was hard. You had to: • work out the questions • build the logic • automate the template • test it properly • maintain it • persuade lawyers to use another platform That is a lot of friction. But in the last couple of weeks, I’ve seen several demos from different vendors that feel like a real step change. Not just “AI helps fill in a few fields”. I mean tools that can analyse a template, identify the variables, suggest the questionnaire, map the logic, and take a huge amount of the heavy lifting out of the automation process. Automatic automation. And the quality is now much better than the early versions I saw even a year ago. The second big shift is how these automated templates are starting to plug into GenAI assistant tools. Instead of a lawyer having to leave their workflow and go to a separate document automation platform, they could ask their AI assistant: “Draft me a share purchase agreement based on this term sheet.” The assistant then calls the document automation tool underneath, uses the approved automated template, extracts the relevant information, asks follow-up questions where needed, and produces the document with the correct structure, formatting and logic. That is the bit I find genuinely interesting. Because this is not AI replacing document automation. It is AI making document automation easier to build, easier to access and easier for lawyers to use. With MCP and similar integration approaches, this also starts to become much more realistic across the Harvey, Legora and Claude-style assistant layer. Just this morning, I saw a real demo of Claude doing exactly this, and it was exceptional. That functionality is due to be released by the vendor within the next two weeks. For me, this is where the drafting stack starts to make sense. GenAI for intake, extraction, conversation and orchestration. Document automation for deterministic drafting, approved templates, formatting, logic and consistency. Lawyers get the easier front door. Firms keep the control and quality underneath. That feels much more compelling than asking AI to freestyle complex legal documents from scratch. If you’d like to see demos of some of the tools and approaches I’m seeing in this space, feel free to message me. I’m spending a lot of time reviewing what is genuinely working well versus what is still more promise than reality. And if there’s enough interest, I may run some open group demo/review sessions so people can see a range of approaches in action rather than only firm-specific sessions behind closed doors. 📸 Oliphants in Covent Garden is my go to for ice-cream in a heatwave. You're welcome x

European Commission: Hybrid #AI to Enhance #Legal #Drafting with LEOS The report presents the outcome of a study funded by the European Commission. The study sought to improve legislative drafting by developing AI-based microservices that assist lawyers and policy developers to uphold the rule of law, harmonise the language of legislation, retrieve relevant accurate legal references, enhance drafting clarity, and strengthen semantic connections within legal texts. LEOS, an open-source web editor developed by the European Commission, provides the platform for integrating these AI enhancements. This document describes in detail four use cases in which hybrid AI combined with Akoma Ntoso XML (AKN) is applied to enhance LEOS. The work is done in cooperation with the European Commission’s DG Informatics (Unit A3) and is supported by the ERC HyperModeLex - Hyperdimensional Modelling of the Legal System in Digital Society - and Erasmus+ Jean Monnet LEDS4XAIL - Legal Design and Data Science for Explicable AI in Legal Domain -projects. The first use case, REFERA (Reference Embedding Retrieval Assistant), aims to reduce manual effort and citation errors, by retrieving the most relevant normative references even from incomplete input. The second use case, DEFINA (Legal Definition Assistant), identifies fitting legal definitions to ensure consistency and reuse of legal terminology. The third use case, RECONTA (Recital Connector to Articles), examines the correlation between recitals and legislative provisions, and suggests a way to record these relations in a machine-readable format through AKN-XML metadata. The fourth use case, TREND (Template of Reporting Requirement Engine for Normative Drafting), proposes, based on legal taxonomies and ontologies, templates for reporting obligations to simplify and harmonise the drafting of regulatory requirements. Together, these use cases convincingly demonstrate how AI and semantic annotations in AKN-XML can be used to improve the quality, transparency, and searchability of legal texts. The hybrid AI methodology combines symbolic and statistical techniques, uses embeddings, retrieval-augmented generation, and large language models. The integration of the use cases in LEOS is through an easy-to-use interface with emphasis on ‘explainability’ of AI- generated output. Finally, AKN serialisation is used for the structured representation of legal documents, normative references, and lifecycle metadata such as entry into force and repeal, creating a robust foundation for interoperability and explainable AI in legislative drafting.

11 Hours, 7 Errors, 3 Missed Claims. One draft fixed by AI. 𝗜𝗺𝗮𝗴𝗶𝗻𝗲 𝘁𝗵𝗶𝘀: Your team sends a draft to a partner. She flags 3 support gaps, misnumbered figures, and a novel claim idea left unwritten. Now, your team is fixing details instead of focusing on client strategy. So we ran a test to understand the best solution: Two experienced attorneys drafted manually. One drafter used a Word-native AI assistant. Manual draft: → 11 hours → 7 errors (claim-support mismatches, figure misrefs) → 3 missed claim ideas AI-assisted draft: → 5.2 hours → 0 critical errors → 2 enriched claims via auto-suggestions The result? The AI assistant didn’t just save time. It elevated the entire draft, fewer issues, tighter logic, and ideas surfaced that might’ve stayed buried in the spec. What changed wasn’t just the speed. It was how attorneys used that time: less formatting, more inventive thinking, and better strategy before examiner objections arrive. Instead of reacting to partner comments or post-filing feedback, AI assistants guide the drafter in real time: ✅ Flags inconsistencies instantly ✅ Anchors claims directly to supporting language ✅ Suggests what’s missing, not just what’s wrong Want to apply this? → Review your last draft: how much time went to formatting vs. legal thinking? → Ask your team: how many missed claim angles are found too late, if at all? → Run a side-by-side on your next case: manual vs. AI-supported. Legal quality doesn’t start in review. It starts as you write. What would 5 fewer errors and 6 extra hours mean for your next filing? 👇

Cutting through the AI noise - here are 5 use cases for using generative AI today in a law practice: 1) Having AI draft initial responses to standard discovery requests, pulling directly from client documents and past cases—turning 3 hours of document review into 20 minutes of attorney verification. 2) Using AI to analyze deposition transcripts and build detailed witness chronologies, flagging inconsistencies and potential credibility issues that could be crucial at trial. 3) Feeding settlement agreements from similar cases to AI to generate initial settlement terms, helping attorneys start negotiations with data-backed proposals rather than gut instinct. 4) Having AI review client intake forms and past matters to spot potential conflicts of interest—moving beyond simple name matching to identify subtle relationship patterns. 5) Using AI to draft routine motions and pleadings by learning from the firm's document history, maintaining consistent arguments while adapting to case-specific facts. The real value isn't replacing attorney judgment. It's eliminating the mechanical tasks that keep great lawyers from doing their best work. What specific AI applications are you seeing succeed (or fail) in your practice? #legaltech #innovation #law #business #learning

I'm an applied scientist, I'm in the business of advancing humanity's knowledge of how to apply technology to advance society. Relativity's Applied Science team is heads-down on the next set of advances for legal technology, but I'm going to pause and reflect on some of the growing evidence demonstrating the validity of our approach and how AI is transforming the legal technology field. First, there's the excellent Vals Legal AI Report, benchmarking the ability of AI to perform various legal tasks, meeting and exceeding the ability of attorneys to do the same work: https://www.vals.ai/vlair. In this study, multiple AI tools were pitted against experienced lawyers across seven common tasks (from document Q&A to contract redlining). The outcome? In four of the tasks, at least one AI tool outscored the human lawyers, and in a fifth task the top AI equaled human performance . The AI excelled particularly at more formulaic or data-intensive tasks like document analysis and extraction, while humans retained an edge in a couple of more complex, reasoning-intensive scenarios. Additionally, in "AI-Powered Lawyering: AI Reasoning Models, Retrieval Augmented Generation, and the Future of Legal Practice", researchers conducted the first randomized controlled trial assessing these technologies, assigning upper-level law students to complete six legal tasks using a RAG-powered legal AI tool (Vincent AI), an AI reasoning model (OpenAI’s o1-preview), or no AI. They found that both AI tools significantly enhanced legal work quality, a marked contrast with previous research examining older large language models like GPT-4. Moreover, they found that these models maintained the efficiency benefits associated with use of older AI technologies. Their findings show that AI assistance significantly boosts productivity in five out of six tested legal tasks, with Vincent yielding statistically significant gains of approximately 38% to 115% and o1-preview increasing productivity by 34% to 140%, with particularly strong effects in complex tasks like drafting persuasive letters and analyzing complaints. What am I most excited about? Benjamin Sexton has published a recent collection of anecdotes from across the industry. The anecdotes included point estimates for precision and recall for 16 uses of generative AI to identify relevant documents for production. These users were able to build AI classifiers that achieved on average 80% precision and 95% recall, saving cost, effort, and time for their customers. Legal professionals should no longer be wondering, "Is generative AI ready for legal?" The evidence continues to grow every day well beyond doubt – the real question now is, "How can we integrate it well into our practice?" For those preparing to embrace this transformation, the path forward is clear: identify pilot projects, select trusted AI platforms, and start refining workflows to capitalize on these efficiency gains. #Legaltech #GenerativeAI #eDiscovery

Nobody has mapped this properly. Every legal AI resource I found is US-centric. Built for American contract law, American courts, and American billing structures. So I built the global map myself — with an Indian lens. Here is the legal AI landscape in 2026. What exists across major jurisdictions, what actually works, and what is still catching up. 1) Research and case law Globally, Westlaw AI and Lexis+ AI lead for common law jurisdictions — powerful but expensive and primarily US and UK optimised. For Indian practitioners, Indian Kanoon paired with Perplexity cuts research time by 70 to 80%. SCC Online's AI layer is improving. In the UAE, the Dubai Courts portal is developing AI integration. Singapore's LawNet is ahead of most Asian jurisdictions. The pattern globally: legal databases are adding AI summarisation fast. Quality varies enormously by jurisdiction. 2) Contract drafting and review: Claude is the strongest cross-jurisdiction performer — holds context across long documents better than any competitor. Harvey AI is purpose-built for legal drafting but remains expensive and US-optimised. Spellbook integrates directly into Word and works well for Canadian and UK firms. For Indian, UAE, and Singapore firms, Claude, with a jurisdiction-specific prompt library, outperforms every specialist tool at a fraction of the cost. 3) Practice management: Clio Duo leads globally, but penetration varies. Strong in North America, growing in the UK and Australia, minimal in India, the UAE, and Southeast Asia. The gap in emerging legal markets is real — most firms still run on WhatsApp, Excel, and email. Notion AI, combined with Make or n8n, fills this gap better than any off-the-shelf product available in these markets today. 4) Client communication. No jurisdiction has cracked this category with a purpose-built legal tool. Globally and locally, the firms winning are building custom intake and communication flows using Claude API plus automation tools. This is a wide-open space in every market outside the US. 5) Compliance and regulatory: The most underdeveloped category everywhere. US has Ironclad and ContractPodAi for contract compliance. UK firms use Luminance. India, UAE, and Singapore are largely unserved by dedicated regulatory AI. This is the category to watch globally through 2026 and 2027. The honest summary No jurisdiction has a complete, reliable, locally optimised legal AI ecosystem yet. What every jurisdiction has is world-class general AI that — configured correctly for local law — performs extraordinarily well. The lawyers winning right now in Mumbai, London, Dubai, and Singapore are not waiting for the perfect local tool to appear. They are building with what exists. And building it right. That gap is widening every month. Save this. Share it with a lawyer in any jurisdiction who needs the full picture.

Generative AI is transforming legal practice. Lawyers are using it to draft memos, summarize documents, generate arguments, clean up writing, and brainstorm strategy. And when used well, AI can be a powerful ally. But not every task is a good match for our AI friends. Some uses are downright risky, and others require an extra layer of caution that many lawyers aren’t applying yet. So let’s draw a line in the sand: when not to use AI for legal writing, and when to stop, verify, and take a more deliberate approach. 1⃣ The Danger Zone: When AI Has to Figure Things Out for You Let’s start with the high-risk cases: the ones where AI should probably not be driving the work. AI is at its riskiest when you’re asking it to find the right legal answer for you—especially if you don’t already know what a good answer looks like. 2⃣ Use Extra Caution: When AI Might Be Helpful But Still Needs Oversight Some tasks fall into a middle ground. AI can help, but only if you stay in control and do rigorous checking. Also, if you’re working from important source material—like a deposition, contract, or statute—feed it in directly. Never assume AI can fill in the blanks accurately. 3⃣ The Safe Zone: When You Know the Substance, and AI Works From Your Input Now for the good news. When you stay in control of the substance, AI becomes an incredibly safe and useful writing partner. In these situations, you're not outsourcing your brain—you’re enhancing it. AI becomes an assistant, not an author. 4⃣ Final Tip: Don’t Confuse Confidence with Accuracy Lawyers are trained to doubt, question, and verify. That doesn’t change just because your assistant is a chatbot. The best use of AI right now is when you know the answer and want help saying it better, faster, or cleaner. So use the tools. Use them often. But use them wisely. - I’m Joe Regalia—law professor and legal writing trainer. Follow me and tap the 🔔 to stay updated on every post.

Human expertise + AI is the most powerful combination in contract review right now. But only if you structure it right. When I was rolling out an AI contract review tool for my legal team, I realized we didn’t just need a tool. We needed a workflow that kept the attorney in charge while leveraging what makes the AI valuable. So I created the Oreo Cookie Method: two attorney-driven reviews on the outside (the cookies), three AI-assisted steps in the middle (the cream filling). Here’s how it works: 🍪 Step 1 — Attorney Review #1: Context and comprehension. Read the contract. Understand the deal. Get the business context you need. You cannot effectively direct an AI through a contract you haven’t read yourself — and no tool can gather that context for you. 🤍 Step 2 — Playbook: Issue spotting. Run your company-built playbook against the third-party template. The AI flags issues and recommends changes based on your organization’s positions. You decide what to apply, what to modify, and what to set aside. 🤍 Step 3 — Review: Diving deeper. Run a general AI review of the current draft from your party’s perspective. This catches what the playbook wasn’t designed to catch — broader legal concepts, jurisdiction-specific considerations, and anything outside your standard template. 🤍 Step 4 — Ask: Targeted cleanup. Use the AI’s prompt-based features for specific tasks: defined terms, cross-references, open items. The attorney identifies what still needs attention. The AI executes. 🍪 Step 5 — Attorney Review #2: Customize and finalize. Take it back. Review every redline. Sharpen what matters, cut what doesn’t. Write explanatory comments that reflect your actual judgment and strategy. Own every markup before it goes out the door. The AI brings speed, consistency, and coverage. The attorney brings context, judgment, and strategy. Together, they produce something neither could pull off alone. The ultimate combination of contract super powers! #ContractReview #AIinLaw #LegalOps #ContractRedlining #oreocookiemethod

Do you trust AI in your legal work? Every week, lawyers hear about another AI tool that “does it all.” But here’s the truth: AI is not a magic lawyer it’s a powerful assistant if used right. A smarter approach to AI in legal practice: 1️⃣ Separate tasks by risk ↳ Use AI for repetitive, low-risk work (drafting templates, summarizing contracts), not for giving final legal advice. 2️⃣ Focus on strengths ↳ Summaries, pattern recognition, first drafts, metrics tracking. Avoid relying on AI for complex reasoning. 3️⃣ Test first, scale later ↳ Run small experiments, measure accuracy, and evaluate if it actually saves time. 4️⃣ Always verify ↳ Cross-check AI outputs against statutes, case law, and firm precedents. 5️⃣ Learn continuously ↳ Stay updated, share insights with your team, and refine which tools truly add value. The goal isn’t using every tool. It’s using AI where it’s reliable, safe, and impactful. Are you trusting AI blindly, or using it strategically?