Whenever I attend presentations on using generative artificial intelligence (AI) in law practices, the presenters always emphasize the value of drafting clear, thorough prompts. And, rightly so. A well-thought-out query will elicit the most on-point response from generative AI chatbots.
The problem is that lawyers start to view perfectly drafted prompts as a condition precedent to AI use. And that’s simply not the case.
Many of us have perfectionistic tendencies. There’s a reason for that. The practice of law can be complex, and attention to detail is essential. It ensures that you’ve carefully reviewed all relevant information, cases, laws, and regulations — and that all subsequent actions are foundationally grounded in accurate factual and legal analysis.
If you overlook a fact or point of law, your conclusions and subsequent recommendations to your clients could be inaccurate, and your license could be on the line.
Usually, perfectionism serves us well, resulting in happy clients — and a dearth of legal malpractice claims
Prompt Paralysis: The Lawyer’s Dilemma
However, our desire for perfection can cause prompt paralysis. As a result, fear of the imperfect prompt can be a significant barrier to AI adoption. After all, the easiest way to avoid the possibility of failure is to avoid all risk, which is exactly what we were trained to do.
So when I hear my well-meaning colleagues wax poetic about the art of perfect prompting as the key to effective generative AI use, I have to resist the urge to raise my hand and offer a reality check.
But good news! This isn’t someone else’s talk, it’s my blog post. The soapbox is mine, and I’ve got a message for you: forget about the prompt.
Instead, choose a generative AI tool and start using it right away. The rest will follow.
Start Talking To AI Like It’s An Assistant
I like to think of generative AI as a compliant assistant sitting on my shoulder who is eager to please, but has a pathological lying problem. I talk to it just as I would a human assistant. I ask questions about a topic I want to learn more about. I request opinions on an issue. I use it for brainstorming. I request its help in composing emails or short messages.
Sometimes my initial query doesn’t elicit the response I’d like. Other times, I realize I left out an important fact or failed to articulate my goal clearly. In those situations, I pivot, add more information, and ask again.
Once you use generative AI tools for a few days, you’ll find yourself asking the same types of questions repeatedly. Your workflows and tasks will determine which requests are inputted most often.
Each interaction will teach you something — about the tool, about your goals, and about how to move from question to answer more effectively. Over time, your prompts will gradually take shape, refined by experience rather than driven by a need for perfection.
Once you find yourself bemoaning the repetitiveness of entering the same query over and over, you’ll realize that you’ve created your first prompt organically. Copy it, paste it into a document, and edit it based on your learnings. Lo and behold, you’ll have your first perfect prompt! Lather, rinse, and repeat for all of the other routine requests you frequently make.
You’ll soon realize that perfect prompts arise from regular use of these tools. Use generative AI daily, and you’ll have a handful of prompts that you copy and paste into the tool. That being said, you don’t need carefully crafted queries for every interaction with generative AI. The vast majority of the time, fluid conversations work fine and get you what you need.
It’s also important to understand that the concept of prompting will soon be obsolete. As the technology advances, many tools will be designed for your specific use case. This is especially so for legal needs. This means that the interface and databases supporting the generative AI tools will be able to intuit what you’re trying to accomplish. The legal-specific tools will be able to anticipate your requests and needs and provide the desired response.
The bottom line: You don’t need a perfect prompt to start. You just need to dive in, choose a tool, and start experimenting. Let the process unfold naturally. Some responses will miss the mark. Others will surprise you.
Don’t let the fear of getting it wrong prevent you from getting started.
Nicole Black is a Rochester, New York attorney and Principal Legal Insight Strategist at AffiniPay, parent company of MyCase, LawPay, CASEpeer, and Docketwise. She’s been blogging since 2005, has written a weekly column for the Daily Record since 2007, is the author of Cloud Computing for Lawyers, co-authors Social Media for Lawyers: the Next Frontier, and co-authors Criminal Law in New York. She’s easily distracted by the potential of bright and shiny tech gadgets, along with good food and wine. You can follow her on Twitter at @nikiblack and she can be reached at niki.black@mycase.com.
The post You Don’t Need To Be A Prompt Whisperer To Start Using AI appeared first on Above the Law.