AI Creativity Unleashed: Expert Insights from Vanderbilt’s Dr. Jules White

Written by Jessica Schulze • Updated on

Discover how refining your approach to AI can protect and enhance your creative vision.

A portrait of Dr. Jules White, computer science professor and Vanderbilt’s Senior Advisor on Generative AI, on a graphic that says GenAI and Creativity

Dr. Jules White is an internationally recognized software engineer and Vanderbilt’s Senior Advisor on Generative AI. He’s been celebrated by the National Science Foundation, published more than 170 papers, and worked as Vanderbilt’s Senior Advisor to the Chancellor on Generative AI in Enterprise & Education. At Coursera, he’s taught thousands of students through popular courses on GenAI, prompt engineering, and ChatGPT. But before he was an AI thought leader, Dr. White was a visual arts major. His appreciation for the arts has informed his perspective on AI throughout his career. 

Dr. White’s unique approach to AI blends creativity with technical strategy. He wants people to think of AI as a resource for creative exploration rather than approaching it as simply a tool that provides straightforward answers.

“It's like somebody handed me a new palette that I can paint with, so what can I go and create?” he says.

This three-part interview series explores Dr. White’s compelling vision for prompt engineering, where creativity is the key to unlocking GenAI's full potential. 

Use GenAI to generate different ideas and different perspectives. I think that’s the mentality we need to cultivate and the way to think about it from a creative perspective.

The art and science of prompting

Before ChatGPT was released to the public at the end of 2022, Dr. White had a PhD student who was experimenting with the early versions of the generative pre-trained transformer (GPT) model. The student kept telling him how impressive it was, but Dr. White was hesitant to fully engage. After the student graduated and ChatGPT launched, Dr. White received a text: 

“You really have to go look at ChatGPT.”

Dr. White’s interest was piqued, but he felt an immediate resistance. As a software engineer, he didn’t want the tool to perform tasks that were so similar to his own work. But as he spent more time with it, its immense creative potential dawned on him. 

“I was on the phone with my dad and we asked it, ‘What would change in the world if we didn't have odd numbers?’ It gave a spectacular answer to this really hard question about all the things that would change and how we might approach it, and I thought, that's not something a computer has been built to answer before,” he says. “Now, it’s one of the building blocks in a computer I have to answer or imagine answers to questions.” 

Dr. White's work emphasizes both the art and science of prompt engineering. Prompting is the input you use to generate responses from a large language model (LLM). Prompt engineering takes this a step further to strategically refine your queries for more accurate and useful results. This more precise approach helps preserve your creative process as you use AI to support your productivity and problem-solving. While considered a technical skill, it also relies heavily on creative thinking. 

“It’s like when you go to a museum—the goal typically isn't to see one painting and copy it … but to see a breadth of different ideas about how to express something, be inspired by it, and then come up with your own,” he says. “Use GenAI to generate different ideas and different perspectives. I think that’s the mentality we need to cultivate and the way to think about it from a creative perspective.”

Preview video image

Dr. White discusses the biggest challenge facing prompt engineering beginners.

On using creativity to improve your prompts

As a professor of computer science at Vanderbilt University and Coursera instructor, Dr. White has guided hundreds of thousands of students through complex subjects like cybersecurity and mobile cloud computing. In the last year, Dr. White has focused on integrating GenAI into his courses, covering a wide range of topics from ChatGPT meal planning to data analysis with Excel. The most common challenge he’s observed among prompt engineering beginners is treating it like an internet search.

“Getting people to think about how to tell it to solve problems rather than answer plain questions is step one. Step two is getting people away from the idea of using it to generate an answer, and instead using it to support their decision-making or problem-solving,” he says. 

To explain, Dr. White shares the familiar example of drafting an email. 

“If you want it to give you an answer you’ll say, ‘Write this email.’ If you're thinking about, ‘How do I use it to support me,’ you’ll analyze it and think of the perspective of the other person—What might be their motivations? What are their concerns?— to communicate your points while also being sensitive to theirs,” he says. “The goal isn’t to have AI write you a bad version that you either edit or decide is terrible and throw away. The goal is really to inform your thinking…It’s something to help you arrive at a better email than you could have written before."

Prompting creativity in action

Here’s an example of what Dr. White’s thoughtful prompting advice for drafting an email might look like in action: 

Basic prompt: “Write an email to my colleague asking for an update on the project.”

AI output: "Hi [Colleague's Name], I hope you're well. Can you please provide me with an update on the project? Thanks!"

Thoughtful prompt: "My colleague mentioned they’ve been busy with other priorities. I want to write them an email to ask for a project update but also offer help where I can. Can you provide me with a few options?"

AI output: 

Option 1: Analytical: ‘Hi [Colleague's Name], Thanks for letting me know about your current workload. I appreciate all the hard work you're putting into the project. When you have a moment, could you share an update on where things stand? Let me know if I can help with anything to move things forward. Best, [Your Name]’

Option 2: Casual and friendly: ‘Hey [Colleague's Name], I hope things are going well, even with all the other projects you're juggling! When you have a chance, could you share a quick update on the project? No rush at all—just let me know what’s needed from my side. Thanks, [Your Name]’”

The basic prompt generated a straightforward email asking for an update without considering the colleague's context or the tone of the relationship. The thoughtful prompt enabled the AI to craft two nuanced and considerate responses. Prompting more than one option offers additional perspectives to consider and the flexibility to mix and match sentences to customize your communication style. 

Check out the article AI Problem-Solving Tactics: Expert Insights from Vanderbilt’s Dr. Jules White for more hands-on prompting techniques.

Placeholder

Keep learning about prompt engineering from Dr. Jules White

Dr. White’s approach to prompt engineering helps reinforce AI’s place in the world as a tool for innovative problem-solving rather than a shortcut to the answers. In Vanderbilt University’s Prompt Engineering Specialization with Dr. White, you’ll learn how to increase the quality of AI outputs in and out of the workplace for more trustworthy results that build upon, rather than replace, your creative vision.

In the next installment of Expert Insights with Dr. Jules White, we’ll explore how leaders can thoughtfully and effectively incorporate AI without stifling creative potential or overestimating the value of automation. And in the third article of our series, we’ll take a closer look at hands-on AI problem-solving techniques. Want to go deeper? Keep exploring the exciting world of prompt engineering with Dr. White in our full video interview.  

Updated on
Written by:

Writer

Jessica is a technical writer who specializes in computer science and information technology. Equipp...

This content has been made available for informational purposes only. Learners are advised to conduct additional research to ensure that courses and other credentials pursued meet their personal, professional, and financial goals.