Prompt Engineering, its Application to the Law and a recent article by McKinsey

Prompt Engineering is my favorite subject and so from time to time I google the phrase to see the latest. Today the number one ranked article was by the consulting giant, McKinsey and Company . What is prompt engineering?Prompt engineering is the practice of designing inputs for AI tools that will produce optimal outputs (McKinsey Insight, 3/22/24). I was pleasantly surprised by the short and sweet content and so decided to share it here. (NOTE: I have no connections with McKinsey and Company, nor do they even know I'm writing this positive review, no one is paying me to do this, etc.)

McKinsey's article offers a nice quick peek into how prompt engineering can effectively harness the capabilities of generative AI. For legal professionals and those intrigued by the intersections of technology and daily operations, prompt engineering is an essential skill.

What is Prompt Engineering?

Prompt engineering ("PE") is about crafting inputs that coax the best possible responses from AI models. I like to call it PE for nerds!

McKinsey's article offers a good foodie analogy of what PE is all about. Although I am not a good cook, my wife is one of the best. I have become a foodie by association (sort of like guilt) and am skilled at appreciation. I need only be prompted by taste tests. Anyway, here is how McKinsey begins their insight article, which was, for me, a great hook.

Let’s say you’re making spaghetti marinara for dinner. Sauce from a jar is perfectly fine. But what if you buy your tomatoes and basil from the farmers market to make your own sauce? Chances are it will taste a lot better. And what if you grow your own ingredients in your garden and make your own fresh pasta? A whole new level of savory deliciousness. Just as better ingredients can make for a better dinner, better inputs into a generative AI (gen AI) model can make for better results. These inputs are called prompts, and the practice of writing them is called prompt engineering. Skilled prompt engineers design inputs that interact optimally with other inputs in a gen AI tool.

The Role of Prompt Engineering in AI

McKinsey's exploration goes beyond the great opening analogy, which I for one suspect ChatGPT4 helped them write. PE is a critical component in the broader framework of AI development. It is GIGO all over again. Good prompts can create golden results, whereas garbage prompts ... you know the rest. I like McKinsey's recipe analogy because it simplifies the concept and highlights the practical applications of crafting precise prompts. PE can significantly improve the output quality of all AI systems, from automating customer service responses, to generating legal documents.

I asked ChatGPT4 to help me with another simple explanation of PE, one that uses the style of a Child Prodigy. She is one of my favorite AI expert panelists as shown for instance by my recent article. Evidence that AI Expert Panels Could Soon Replace Human Panelists, or is this just an Art Deco Hallucination? – Part One of Two (EDRM, May 9, 2024). Here is the genius child's summary of prompt engineering:

Prompt engineering is like giving really good instructions to a computer program to help it do tasks better. Imagine you have a super smart robot friend who needs to know exactly what you want before it can help. You have to tell it step by step what to do, like explaining a game to a friend, so it doesn't get confused. This helps the robot understand better and do its job right, especially when things are a bit tricky!

As you can see, this AI kid is much smarter than me, although I did prompt her into existence.

The McKinsey Perspective: Insights and Implications

The McKinsey article provides a good perspective on the implications of PE for business and society. By improving prompts, we can leverage AI to handle complex tasks previously thought beyond the reach of automation. This includes areas like drafting detailed legal arguments or synthesizing vast amounts of case law into comprehensible summaries.

McKinsey estimates that generative AI and technologies like it "have the potential to automate work activities that absorb up to 70 percent of employees’ time today." For the legal profession, this could signify a transformative shift in how paralegals and attorneys allocate their time, focusing more on strategy and less on menial tasks.

McKinsey goes on to repeat the prediction it made over a year ago that there will be a $4.4 trillion addition to the economy from generative AI. There will be more jobs, not less, albeit new jobs, many of which are not existing yet.

McKinsey’s latest research suggests that gen AI is poised to boost performance across sales and marketing, customer operations, software development, and more. In the process, gen AI could add up to $4.4 trillion annually to the global economy, across sectors from banking to life sciences.

I talked about this prediction previously in my article, McKinsey Predicts Generative AI Will Create More Employment and Add 4.4 Trillion Dollars to the Economy (e-Discovery Team, 6/23/23). In my article I concluded:

The McKinsey Report provides clear warning of the coming storm of generative Ai. There are great opportunities and dangers. McKinsey is trying to prompt all of us to take action now. Quick action does not come easily to the legal profession. Lawyers suffer from a common affliction of the over-educated,?paralysis by analysis. We tend to think too much and act too little. We are consumed with the fear of making a mistake. That is especially true when thinking about something new and strange.

As I pointed out in my article last year, which remains true today, the time for action by the legal profession is now.

In times of rapid change, like we are living through now, we must resist the temptation to just sit back and do nothing, or worse, appoint a committee to study the situation. Long gone are the leisurely days of taking years to consider and implement new rules and procedures in the law. If the legal profession is to make a smooth transition, not only survive, but prosper and provide the justice services our world desperately needs, then we must all realize that weakness. As McKinsey concluded, all of us?must act-and quickly, given the pace of generative AI adoption.

This call to action is even more imperative today.

Conclusion: A Call to Embrace AI Innovations

For those of us in the legal field, McKinsey's top ranked article on prompt engineering challenges us again to rethink our relationship with technology, to embrace AI not just as a tool, but as a partner. The whole world, including the legal profession, stands on the brink of a great leap in technology. This change is just beginning. ChatGPT4 just just been out a little over a year. Although there are nay sayers, I for one think it will keep getting better.

The future of law is not just about understanding the laws we have, but also the tools we use to interpret and apply them. PE for nerds is an important part of that way.

Copyright Ralph Losey 2024 -- All Rights Reserved