How Ropes & Gray is developing AI for transactional diligence

openai.com

In transactional diligence, lawyers need to work through large volumes of documents under tight deadlines. Ropes & Gray was an early adopter of AI in the legal industry, and in partnership with OpenAI, they are now developing a proprietary AI tool to provide more expertise to more clients.

“AI is really one of the key ways—if not the only way—to make sure you can maintain the same quality and consistency of advice while moving at a faster pace.”

—Josh Lichtenstein, Partner and Head of ERISA Fiduciary Practice, Ropes & Gray

Building a first pass for commercial contract diligence

Before finalizing any acquisition, the buyer must carry out a thorough investigation to validate the seller’s financial and legal claims. That process of transactional diligence uncovers risks and liabilities, requiring data-heavy research that usually involves an entire team of lawyers.

From parsing through an enormous number of documents to analyzing patterns, putting together a bid on a short timeline can take days of intensive work. To help their lawyers help their clients move more quickly, Ropes & Gray developed a transactional diligence AI tool with OpenAI.

“It’s enabling all the lawyers at our firm to actually get to what we’re supposed to be doing,” says Howard Glazer, the Partner and Head of Practice AI at Ropes & Gray. “Our clients don’t pay us to review contracts. They pay us to make judgments based on what’s in the contracts.”

The new diligence AI tool takes a first pass by combing through thousands of pages, identifying relevant documents and automatically grouping them together based on themes and issues. Along with the research, the tool produces summaries and a completed report in Ropes & Gray’s signature format. It inventories and categorizes a data room, so it can review full relationships, not isolated documents. Of course, lawyers can inspect the grouping and categorization to confirm nothing is missed.

The initial development work has focused on material commercial contracts. In working sessions, Ropes & Gray’s lawyers compared test outputs with human-authored diligence reports from completed deals, then refined the rubric and report format based on what the drafts got right and where they fell short.

Ropes & Gray designed the tool with a consistent query and framework that mimics the exact steps their team would take, from initial reviews to summaries to higher-level reviews. Comparable to the work of a capable junior-to-mid-level associate, this tool gives their firm consistently high-quality work that serves as a first pass through the process.

“Our lawyers still need to review everything,” says Lichtenstein. “Because anything that we’re going to deliver to a client, we need to be able to stand behind 100%. This is why the tool is designed to allow lawyers to easily review interim summaries and actual documents.” With the initial review taken care of, lawyers can spend more time reviewing and refining the work, resulting in a more carefully crafted final judgment.

Applying AI to complex transactions

Ropes & Gray has publicly described an ambition for the tool to produce a detailed, issue-level diligence report in hours rather than weeks.

With tools like their proprietary diligence tool and GPT‑6 Astra, Ropes & Gray has been able to solve client problems far faster than before.

Results at a glance

The tool inventories and categorizes a data room, grouping related documents by themes and issues.
The workflow produces summaries and a report in Ropes & Gray’s format.
Lawyers review interim summaries and source documents before delivering work to clients.
Testing compares draft outputs with lawyer-authored diligence reports to refine the rubric and report format.

Leadership lessons

Lichtenstein and Glazer offer two lessons from their experience with AI.

Experiment with using AI for everything. From finding dress shoes to vibecoding games for his kids, Lichtenstein has been using AI in every facet of his life. “Just by using it for so many different things, I feel like I’ve learned a lot of what it does well, how you can make it work better,” Lichtenstein explains. “The most rewarding part is not when it does well, it’s when you see the mistake and try to figure out what to do. That’s where it transformed from something I was playing with to a really powerful professional tool.”

Put the clients first. While designing AI tools and workflows, Ropes & Gray emphasizes the importance of keeping the firm’s greatest goal in mind. “It’s exciting to think there is so much opportunity, but only if we learn how to use it and make sure that our clients are the ones who are winning,” says Glazer. “That’s what we’re focused on: how can we use this to benefit the clients? And if we do that, then everything will work out fine.”

What’s next