TheCorporateCounsel.net

This time last year, Time Magazine ran the enticing article “The AI Job That Pays Up to $335K—and You Don’t Need a Computer Engineering Background.” The job, of course, was “prompt engineer,” and the article suggested a humanities background might be best for this role. While it was focused on prompt engineering as an AI training tool, prompt engineering is also key to employing generative AI in its various practical applications — since fine-tuning inputs is key to better generative AI outputs.

I must admit that I remain wary of legal applications of generative AI, but this Loeb & Loeb Quick Take on generative AI was a welcome reminder that there’s a fast-moving (now more AI-run) world out there that keeps advancing whether I’m ready or not!  And I better get with the times since the post argues that using gen AI tools “is becoming an essential skill” for lawyers to streamline workflows, improve efficiency and “meet the evolving demands of clients.” Enter the need to “become proficient in ‘engineering’ your prompts.”

The post gives six tips to help lawyers improve their “prompt engineering” skills without formal training. Here are a few:

Be Precise: Accuracy and precision are critical when it comes to the law. Avoid ambiguity in your prompts by using clear, concise, and plain language. Aim for a conversational tone, avoid legalese, and explain to the tool the meaning of any acronyms and other abbreviations used in the prompt.

Specify the Why and the What: Clearly state your goal. What information are you seeking? What action do you want the AI tool to take? Once the intent is established, provide specific instructions on the desired output. For example, specify the “voice” you are looking for (e.g., formal, casual, personal, adversarial), and indicate the format you want for the output (e.g., a summary, an analysis, a draft, a bullet-point list, a table, a deck slide, an email correspondence, a blog-post, etc.).

Iterate and Refine:  Leverage the chat-based nature of GenAI tools. You can have a back-and-forth conversation with the tool, providing additional context and tweaking prompts on an iterative basis.  Try starting with a basic question, then keep refining the prompt (such as by adding more context and specificity, identifying problems with the output from an earlier prompt, and/or changing the tone or terminology) as needed to steer the AI tool towards a more relevant and focused output.

Despite my AI reluctance (is that an official term yet?), I do recognize the value in developing these skills. So I’ve started leveraging ChatGPT for some low-risk personal applications — things like creating vacation itineraries, meal plans & grocery lists — and have found employing these tips to be crucial to getting useful outputs even for these basic, personal tasks. When I went to check out the “family-friendly restaurants” it recommended for one vacation, I discovered a number of them had closed during the pandemic, which also gave me personal experience & understanding of some of the risks of using generative AI and why it’s so important to do your own work.

– Meredith Ervine