The Attorney’s AI Workflow: Prompt Patterns, Live Demos, and the Verification Habits That Keep You Off the Sanctions Docket

Adam G. Gutbezahl, Shareholder | Ruberto, Israel & Weiner, P.C

Adam Gutbezahl speaks and writes extensively on the legal implications of generative AI, serves on multiple steering committees and task forces addressing its use, and publishes ChatAdamG, a monthly newsletter covering the legal perspective on AI in the workplace. He is a shareholder in the Litigation Department at Ruberto, Israel & Weiner in Boston, where he represents individuals and businesses in complex commercial, employment, land use, and real estate disputes. He has jury and bench trial experience in state and federal court, and in 2024 served as first chair for two RIW trial teams, achieving favorable outcomes in both cases.

• Education & Credentials

Adam earned his J.D., cum laude, from The George Washington University Law School in 2013, where he served as an executive editor of The George Washington Law Review and as a member of the Moot Court Board. He holds a B.A., cum laude, from The George Washington University (2006). He is admitted in Massachusetts and before the United States District Court of Massachusetts, the United States District Court for the Eastern District of Michigan, and the U.S. Court of Appeals for the First Circuit.

• Recognition & Leadership

Adam received the National Business Institute’s Outstanding Faculty Award (2023). He has been named a Massachusetts Lawyers Weekly Excellence in Law Up and Coming Lawyer (2025), a Massachusetts Super Lawyers Rising Star in Real Estate (2024, 2025), a Boston Magazine Top Lawyer (2024, 2025), and one of the New England Real Estate Journal’s Ones to Watch – Rising Stars (2024). He was selected for the Boston Future Leaders Program, a 10-month leadership initiative by Harvard Business School and the Greater Boston Chamber of Commerce (2024), and was the MetroWest Chamber of Commerce’s Emerging Leader of the Year (2022).

• Professional Involvement

Adam serves on the Boston Bar Association’s Privacy, Security, & Digital Law Group Steering Committee and its Curriculum Advisory Committee, and is a member of the American Bar Association’s Artificial Intelligence & Robotics Group, the Massachusetts Bar Association’s Business Law Artificial Intelligence Practice Group, the Massachusetts Real Estate Bar Association’s Artificial Intelligence Task Force, and the Greater Boston Chamber of Commerce’s Future Tech Leadership Council. His community roles have included the Performing Arts Center of Metrowest Board of Directors (2022–2026) and the Wayland Trust Fund Commission (2019 – Present).

• Experience

Adam’s recent programs on generative AI include “Top ChatGPT and Generative AI Blunders Paralegals Are Currently Making” for the Institute for Paralegal Education (February 2026), the Boston Bar Association panel “Generative AI in Business: Ethical, Legal, and Practical Considerations for Lawyers” (February 2025), and “Balancing Efficiency & Ethics: AI in the Legal Profession” for Pilgrim Advocates (October 2025). He has presented twice for myLawCLE audiences: “Practical AI Tools for Litigators: Strengths and Weaknesses” (August 2024) and, with the Federal Bar Association, “ChatGPT and Generative AI: Transforming Estate Planning Strategies” (February 2024). His writing on the technology includes “Is Your AI Use Protected from Disclosure? It’s Complicated.” (August 2026) and “ChatGPT in the Workplace: Employers Beware” (June 2023).

In his litigation practice, Adam obtained summary judgment in land use disputes, secured a complete judgment for homeowner clients — including an award of attorneys’ fees under M.G.L. c. 93A — after a five-day jury trial in Middlesex Superior Court, and negotiated settlements across employment, contract, and tort-based claims. He counsels clients on best practices to avoid litigation and mitigate risk.

Steve Smith, Founder & CEO | Intelligence by Intent

Steve Smith is the founder and CEO of Intelligence by Intent, a legal AI advisory firm that helps law firm leaders turn AI from scattered experiments into a compounding advantage. Since 2023, he has trained more than 3,500 attorneys across 100+ firms and bar associations, delivering CLE-accredited keynotes and hands-on workshops for organizations including AAML, BHBA, LACBA, and SFVBA.

• Education & Credentials

Steve holds an MBA from the Wharton School (WG’98). He also holds a BBA from Loyola Marymount University, and appears as Stephen M. Smith on bar association and AAML programs.

• Recognition & Leadership

Steve brings an operator’s perspective to legal AI. Before founding Intelligence by Intent, he spent 25 years in various technology and strategy organizations. He has held CEO, CFO, and SVP roles, including CFO of TSIA, SVP of revenue operations leadership at 8×8, and strategy consulting partner roles at IBM and TCG Advisors. That background shapes his core message: AI adoption is a revenue, efficiency, and governance problem that happens to involve technology. He was invited to write “The Family Lawyer’s Field Guide to AI” for the Journal of the American Academy of Matrimonial Lawyers (forthcoming).

• Professional Involvement

He writes several times a week at smithstephen.com, read by over 2,000 senior executives with more than 400,000 article views across Substack and LinkedIn. His speaking engagements also include the California Lawyers Association and myLawCLE with the Federal Bar Association, and he has written more than 300 articles on legal AI since 2023.

• Experience

His work spans executive workshops, firm-wide training, AI governance and usage policies, and case support on live matters, all grounded in a library of 200+ legal-specific use cases built in firm conference rooms, not theorized. He is based in Los Angeles, working with firms nationally. He is independent of every AI vendor — he does not sell or resell any tool he trains on — and tests every major model from Anthropic, OpenAI, Google, and xAI the week it ships, writing up what changed for law firms. His client work centers on managing partners at firms of 10 to 100 attorneys who need partner buy-in before investing in AI, COOs fielding daily AI questions from associates and partners, and litigation teams whose matters turn on a large record. He is not an attorney — he makes the tools, the processes, and the training useful to lawyers, and the legal judgment stays with them.

SESSION 1 – Foundations: Getting Reliable First Drafts from AI | Adam Gutbezahl | 11:00am – 12:00pm

The on-ramp hour, built for attorneys who have opened a chat window and been underwhelmed. The session establishes what large language models actually do and where they fail, in plain terms, then builds the anatomy of an effective legal prompt one element at a time: role, context, task, format, constraints. Three live demonstrations put that structure to work on the tasks that return time immediately, each ending with its prompt pattern displayed full-screen and reproduced in the prompt library. No AI background assumed at any point.

BREAK | 12:00pm – 12:10pm

SESSION 2 – Advanced Workflows: Real Matters, Start to Finish | Steve Smith | 12:10pm – 1:10pm

For lawyers who already use AI every week and want to see what it can do with a full matter file. The session runs about 15 demonstrations drawn from family law, construction and business litigation, estate and trust, and insurance coverage. Each one starts with a realistic document set and ends with work product a supervising attorney would actually review. You’ll watch AI build a sourced chronology from a deposition and its exhibits, flag where the testimony and the documents disagree, and carry that into a draft declaration. You’ll see a signed stipulation turned into a docketing list with every deadline tied to the language that triggers it. And you’ll see the supervision habits that make this work safe on a client matter, from review stops between steps to a verification pass before anything leaves the room. Every file is fictional.

The session moves through chained workflows, in which a deposition and its exhibits become a sourced chronology, then an issue outline, then a draft declaration or motion section, with a review stop at each handoff. It demonstrates working across a document set, synthesis across a full matter file, including a contradiction register that shows exactly where the witnesses and the record part ways and exception-first review, with risk-spotting on an incoming contract and a structured critique of an opposing draft, problems surfaced first and every finding tied to its page. On orders and deadlines, a stipulation, MSA, or judgment is converted into a calendaring list with the trigger language quoted and each date held as unverified until a person checks it.

Attendees also keep the tools and patterns behind the demonstrations: interactive settlement models and an intake summarizer built in conversation with no code, plus Projects and Skills that hold format and constraints steady from one matter to the next. The session closes with catching failure mid-workflow, spotting the signs that output is slipping, like a deadline that lands on a Sunday or a citation nobody can find and recovering without starting over.

BREAK | 1:10pm – 1:20pm

SESSION 3 – The Verification Hour: Ethics Checkpoints from Prompt to Filing | Adam Gutbezahl | 1:20pm – 2:20pm

A working ethics hour organized around the path from AI output to filed documents. It walks the pre-filing verification protocol step by step, citations, quotations, factual assertions, then moves to the confidentiality settings that determine what a model remains under Rule 1.6, and the supervision policies Formal Opinion 512 and Rules 1.1, 5.1, and 5.3 expect once associates and staff touch these tools. The current sanctions landscape supplies the stakes, not the syllabus. (1 Ethics Credit)