Benefits of generative AI: I didn’t know it could do that!

Sterling Miller
Senior Counsel for Hilgers Graben, PLLC

“Turing proposed that a human evaluator would judge natural language conversations between a human and a machine that is designed to generate human-like responses. The evaluator would be aware that one of the two partners in conversation is a machine, and all participants would be separated from one another. The conversation would be limited to a text-only channel such as a computer keyboard and screen so that the result would not be dependent on the machine's ability to render words as speech. If the evaluator cannot reliably tell the machine from the human, the machine is said to have passed the test.” - The Turing Test

In Part 1 of this refresh of my 2017 series on artificial intelligence, we discussed how artificial intelligence works and the immediate and substantial impact of generative artificial intelligence since its advent in late 2022. In Part 2, we looked at whether such tools would replace lawyers wholesale — fortunately, no. What should be clear is that the legal industry and profession are on the cusp of a second revolution in the practice of law led by the use of generative AI — a revolution that will be led by in-house lawyers more so than law firms. In Part 3, we look closer at the many practical use cases for and benefits of generative AI (GenAI) in legal departments. 

Before identifying the many practical ways legal departments are using generative AI, let's keep one essential fact in mind: technology doesn’t get tired, sleep in, call in sick, or take vacations, and it doesn’t need breaks for food or when nature calls. Technology just keeps working and working and working. That is a huge benefit to any company and its legal department. But — and there is always a but — technology always needs a human nudge to get started with whatever work is required. Otherwise, it just sits there waiting for someone to ask it to do something. In other words, generative AI is not a self-starter. 

The prompt 

Leading us back to something we touched on in Part 1 is the critical nature of the “prompt” in the use and continued development of generative AI. Without prompts — or well-thought-out prompts — generative AI is basically a potted plant or a misdirected assistant. So, let’s discuss prompts! 

Generative AI works by attempting to understand your question — your prompt. Once prompted to do something, it starts setting out strings of words that it predicts will provide the best answer, all based on — and currently limited to — the data set it was trained on. In short, it scans a ton of information and writes the best answer possible based on the data it has access to — just like you do as a lawyer, only at a much slower pace, albeit with innate human skills that AI cannot yet, if ever, duplicate. Generative AI uses a deep-learning neural network, which is a super-complex computer algorithm modeled after the human brain to do the predicting. This network allows generative AI to learn patterns and relationships in the data set and then create human-like responses by predicting what text should come next in any given sentence. Of course, there’s more to it than this, but this isn’t Scientific American, and you, like me, probably don’t care much about this part. 

Prompts are questions, instructions, or requests that you type into the GenAI tool to trigger the process described above. The exciting part is that you are not limited to a single prompt and response. You can ask generative AI multiple questions, make multiple requests as part of one prompt, or refine the results by refining the prompt or adding to the data it’s considering. This ability is the vast improvement brought about by ChatGPT vs. early AI tools. It takes practice and time to get it right, and the latter is something most in-house lawyers don’t have a lot of. So, you need to balance the potential gains from utilizing generative AI with the cost in terms of time spent and, as I will discuss in Part 4, sometimes crummy or bizarre results.

I think the best way to think of prompts and generative AI is to treat the tool and process like you would treat a young associate or intern. By that, I mean you must brief it on what you want, give additional information throughout the assignment, ask clarifying questions, and, in the end, likely fix the work product. But let’s walk before we run. Here are some simple ChatGPT prompts I have created or found that make it easy to get started:

  • What is the standard for [set out legal issue] in [x] jurisdiction?
  • Outline the steps needed to do [y]
  • Create a checklist for [x]
  • Draft a contract for [scenario]
  • Prepare a presentation from the legal department to the business on [topic]
  • Can you provide cases that discuss [specific legal issue]?
  • Summarize this agreement and identify the five most important terms
  • Prepare a term sheet for [name] type of deal containing these key terms [list]
  • Write [x] in the style of a business person and not like a lawyer 

For more information on ChatGPT prompts:

Again, in Part 4, we will discuss some of the shortcomings of ChatGPT/generative AI in the legal context, but for now, just know that you need to:

  1. Use hypotheticals vs. real client names
  2. Use your judgment to consider what generative AI is giving you
  3. Check the work if you have asked for specific statutory or case law analysis, just like you would for a summer associate or intern 

What can generative AI do right now?

In 2017, I wrote about what AI could do or was already doing, including e-discovery review, due diligence, contract preparation, contract management, legal operations analytics, litigation analysis, legal research, etc. Not bad, but — as I can see now, six years later, with the benefit of hindsight — somewhat limited and primitive. Generative AI does all this better, faster, and cheaper. It does so much more that is incredibly useful to in-house lawyers. This is the part that has truly blown me away — the extremely long list of things that GenAI can do for in-house lawyers right now:

  • E-discovery document review 
  • Legal research 
  • Draft legal briefs and motions
  • Offer general strategies or steps for managing business crises or PR challenges 
  • M&A due diligence
  • Jury research
  • Assist in performing a strengths, weaknesses, opportunities, and threats (SWOT) analysis for a legal or business scenario
  • Contract drafting and analysis 
  • Deposition prep kits

The underlying theme here is that while older versions of artificial intelligence tools were excellent at barfing up information, generative AI can create, mimicking a lawyer’s ability to gather information — old AI — and draft something incorporating that information into useful work product — generative AI — in seconds. In that vein, one exciting writer on the practical uses of ChatGPT by in-house lawyers is Laura Greenberg. She has written a series of articles on how in-house lawyers can use ChatGPT to make contract preparation and negotiation easier and faster, including how to use ChatGPT to draft explanatory comments in contracts and using ChatGPT to create a contract negotiation table. There are also other ways lawyers are using ChatGPT.


While lawyers are generally very excited about the possibilities of generative AI, the most significant impact will come from its use by in-house legal departments. The incentive for in-house legal departments to find the fastest, most practical, and lowest-cost way to do things is greater than the incentive for law firms to find ways to offer lower-priced services — for example, quantity of billable hours vs. quality of a billable hour. Indeed, the future is not tomorrow but is truly here today, and legal departments are leading the charge on how best to use this amazing technology. As well-known legal technology companies like Thomson Reuters include generative AI in their services, in-house lawyers will be able to do things faster, better, and cheaper. The possibilities are just too hard to resist. In the final installment of this series, we will discuss some of the current shortfalls of generative AI along with what in-house lawyers should be doing now to take advantage of the benefits the technology has to offer. 

About the author

Sterling Miller is currently CEO and Senior Counsel at Hilgers Graben PLLC. He is a three-time General Counsel who spent almost 25 years in house. He has published five books and writes the award-winning legal blog, Ten Things You Need to Know as In-House Counsel. Sterling is a regular contributor to Thomson Reuters as well as a sought-after speaker. He regularly consults with legal departments and coaches in-house lawyers. Sterling received his J.D., with honors, from Washington University in St. Louis.

Join our AI community

Get trusted answers on AI. Sign up for industry-leading insights, updates, and all things AI @ Thomson Reuters.