Researching and composing an article for my blog can be time-consuming. I usually block out a few hours on a slow weekday afternoon or over the weekend. After a week of meetings and some travel, I realized that much of my Sunday would have to be dedicated to researching and writing this article about developing an AI curriculum.
Selecting the topic that I write about is usually a little harder. There are many things that I could discuss, but writing about an area of interest is easier than writing about a current event or policy change.
My inspiration at this moment for writing about Artificial Intelligence (AI) stemmed from several conversations with acquaintances at a Kentucky Derby party. My first conversation was with a seasoned media professional who currently works for a CBS affiliate in a major city. The second conversation was with a college soccer coach.
A comment from me about the volume of negative political ads currently airing on television triggered a conversation with the media person about deepfake videos, his concern about how deepfakes could influence elections, and the Biden Administration’s initiatives to regulate AI.
My conversation with the coach was more personal. My daughters and his son were classmates at a private school from kindergarten through 12th grade. We exchanged information about what our children were doing now. His youngest child will be a senior in high school next year. He asked what she should study in college to be prepared for AI.
I answered my friend’s question as best as I could without any preparation and within the unofficial five-minute maximum that you are allotted for cocktail party conversations. Later in the evening, I thought about his question some more. I considered spending time perusing college websites for an answer. Instead, I opted to ask ChatGPT4+.
It took me longer to write the first paragraph of this article than it did to write my first prompt and receive ChatGPT’s response. I chose to use ChatGPT4 because it accesses more recent content. My prompts are pasted below, as well as the AI’s responses.
Prompt 1 for Chat GPT 4:
I am a college provost. Like many other colleges, we are struggling to maintain our enrollments. The president suggested that we consider adding a degree in artificial intelligence to our curriculum. Can you recommend how to determine if there is a demand for an undergraduate degree related to artificial intelligence? For a broader audience, should the degree be more oriented toward business rather than programming? Can you also recommend the major topics or courses that should be part of an artificial intelligence degree?
ChatGPT 4’s response to Prompt 1:
Adding a degree in artificial intelligence (AI) can be an attractive option for attracting students, especially given the growing interest and application of AI across various sectors.
Here’s a step-by-step approach to determine if there is demand and how to structure such a degree:
Assessing Demand
- Market Research: Conduct surveys with prospective students, current students, and alumni to gauge interest in an AI degree. Additionally, you can analyze search trends and the popularity of AI-related topics online.
- Industry Consultation: Engage with local and national businesses to understand their current and future needs for AI skills. This can help tailor the degree to be more relevant and attractive to employers.
- Competitive Analysis: Review other institutions that offer AI degrees. Look at their curriculum, enrollment numbers, and graduate success rates to estimate potential demand and positioning.
- Career Prospects Analysis: Explore job market trends for AI roles. Tools like the Bureau of Labor Statistics in the U.S. and job analytics platforms like LinkedIn or Glassdoor can provide insights into the growth of AI-related jobs.
Degree Orientation: Business vs. Programming
- Business-Oriented: A business-oriented AI degree could appeal to a broader range of students, including those interested in management, strategy, and application of AI rather than its technical aspects. This could include courses on AI in marketing, finance, and business analytics.
- Programming-Oriented: A more technical degree would attract students who are interested in the nuts and bolts of AI, such as machine learning, neural networks, and data handling. This is crucial for roles that are deeply technical such as AI developers or data scientists.
Depending on your institution’s strengths and the industry needs in your region, you might consider offering tracks within the AI degree that allow students to specialize in either business applications or technical development.
Suggested Major Topics and Courses
1. Core Computer Science Skills
- Programming (Python, R)
- Data Structures and Algorithms
- Statistics and Probability
2. Foundational AI Courses
- Machine Learning
- Neural Networks and Deep Learning
- Natural Language Processing
- Robotics and Perception
3. Business and Ethics
- Ethical Implications of AI
- Business Intelligence and Data Analytics
- AI Strategy and Management
4. Advanced Topics
- Computer Vision
- Reinforcement Learning
- AI in Healthcare, Finance, or other sector-specific applications
- Practical Experience
- Capstone Projects
- Internships
- Collaborative Research Opportunities
By carefully considering these elements, you can design an AI degree program that not only meets current educational standards but also prepares students for successful careers in a rapidly evolving field.
Evaluating the Response to Prompt 1
I thought the AI gave me a reasonable answer to my question about determining market demand. For the purposes of writing an article for my blog or answering my friend’s question about areas his daughter should study, I would skip the market research surveys and industry consultation.
As I mentioned earlier, I considered reviewing a few colleges’ websites. If I were conducting the research I asked for in my prompt, I would review my primary competitors’ websites. For the Career Prospects research, I would use Lightcast. I prefer Lightcast over BLS. I would also choose Lightcast over LinkedIn and Glassdoor.
I liked the AI’s response to my question about whether the degree should be oriented toward business or programming. I would have preferred more depth in the business write-up.
The response to suggested major topics and courses was interesting in that the AI chose to provide me with a curriculum that is more oriented toward programming, not business. I assume that it responded this way because most AI curriculum is oriented toward programming, and the content used to train the model probably follows the majority.
Prompt 2 for ChatGPT 4
I like the idea of a business-oriented AI degree. What courses would you include if you were asked to design an eight-course curriculum titled Business Applications in Artificial Intelligence?
Chat GPT 4’s Response to Prompt 2
Creating an eight-course curriculum for a degree titled “Business Applications in Artificial Intelligence” provides an opportunity to blend business acumen with AI expertise, aiming to produce graduates who can bridge the gap between technical teams and business strategy.
Here’s a proposed curriculum:
1. Introduction to Artificial Intelligence
- Overview: Basic principles of AI, history, key technologies, and their applications in business.
- Goal: Familiarize students with AI terminology and concepts to provide a solid foundation for more advanced topics.
2. Data Science for Business
- Overview: Introduction to data science, focusing on statistical analysis, data visualization, and predictive modeling.
- Goal: Equip students with the skills to interpret and use data effectively in business decisions.
3. Machine Learning in Business
- Overview: Core machine learning techniques and algorithms and their application in business scenarios like customer segmentation and inventory management.
- Goal: Enable students to implement and manage machine learning projects that solve real business problems.
4. AI and Customer Relationship Management
- Overview: Use of AI in enhancing customer experience, personalization, and customer lifecycle management through chatbots, recommendation systems, and CRM analytics.
- Goal: Teach students how to apply AI tools to improve customer engagement and satisfaction.
5. Business Intelligence and Analytics
- Overview: Advanced analytical techniques and tools for business intelligence, including real-time analytics and dashboards.
- Goal: Prepare students to design and lead data-driven strategies to improve business performance.
6. AI Strategy and Implementation
- Overview: Strategic planning for AI initiatives, focusing on integration, scalability, and ROI. Includes case studies of successful and failed AI projects.
- Goal: Develop skills in strategic thinking and planning for AI, ensuring alignment with business objectives.
7. Ethical AI in Business
- Overview: Exploration of ethical concerns, data privacy issues, and the social impact of AI. Includes discussions on regulation and compliance.
- Goal: Encourage responsible AI deployment with a strong understanding of ethical considerations in a business context.
8. Capstone Project in Business AI
- Overview: Practical project where students apply AI solutions to real business challenges, potentially in collaboration with industry partners.
- Goal: Synthesize learning from the program into a practical, impactful AI business solution.
This curriculum aims to blend technical learning with practical business applications, preparing students to deploy AI technologies in various business contexts effectively. Each course would ideally include case studies and practical projects to ensure that theoretical learning is solidly connected to real-world applications.
Evaluating the Response to Prompt 2
I didn’t time it, but I believe ChatGPT 4 took 15 seconds to display its response to my second prompt. It is possible that the linkage to the first prompt enabled the quicker reply. I don’t know, but the quick response was impressive.
When I first skimmed the course titles, I wasn’t sure I liked the response. However, the Overview and Goal included under each course title provided enough information to help me consider how to build a syllabus for each course.
I debated asking ChatGPT to provide me with a 12-course curriculum since many business degrees consist of at least 12 courses. Naturally, I questioned why I needed to debate the 8 versus 12-course curricula when I could type another prompt. I took the easy way out.
Prompt 3 for Chat GPT 4
The business school faculty reviewed your suggestion for a business-oriented AI curriculum and believe we need to offer 12 courses. What would you propose for a 12-course curriculum?
Chat GPT 4’s Response to Prompt 3
Expanding the curriculum to 12 courses allows for a more comprehensive exploration of topics and the inclusion of some specialized subjects that can further enhance students’ understanding and capabilities in business applications of AI. Here’s a revised and expanded 12-course curriculum:
1. Introduction to Artificial Intelligence
- Basics of AI, key concepts, and overview of its applications in various industries.
2. Data Science for Business
- Fundamental data science skills tailored for business applications: statistics, data manipulation, and visualization.
3. Machine Learning in Business
- Introduction to machine learning with practical applications in business scenarios like predictive analytics and decision-making.
4. AI and Customer Relationship Management
- How AI can enhance customer interactions and personalization through CRM systems, chatbots, and recommendation engines.
5. Business Intelligence and Analytics
- Techniques and tools for extracting actionable insights from big data, focusing on dashboarding and reporting.
6. AI Strategy and Implementation
- Planning and managing AI projects within organizations, emphasizing strategic integration and innovation management.
7. Ethical AI in Business
- Discussions on the ethical use of AI, data privacy, and regulatory compliance, with a focus on maintaining corporate and social responsibility.
8. Neural Networks and Deep Learning for Business
- Advanced AI techniques, focusing on their practical uses in areas such as image and speech recognition in business contexts.
9. Natural Language Processing for Business
- Application of NLP in business for customer service, sentiment analysis, document automation, and more.
10. AI in Operations and Supply Chain Management
- Use of AI to optimize logistics, inventory management, and operational efficiencies.
11. AI for Financial Decision-Making
- Leveraging AI in financial services, including algorithmic trading, risk assessment, and credit analysis.
12. Capstone Project in Business AI
- A comprehensive project that integrates all the skills and knowledge acquired, applied to a real business problem in collaboration with an industry partner.
This expanded curriculum offers a broader and deeper exploration of AI in a business context. It incorporates foundational skills and advanced techniques and focuses on specific business functions where AI can be transformative.
Evaluating the Response to Prompt 3
The extra courses added were reasonable recommendations; not great, just reasonable. The AI did not provide the specific Overview and Goal categories under each course that it included in its previous response. Had I structured my prompt to ask it for that format, I’m sure it would have been included. Having that might have upgraded my evaluation of the recommendations as reasonable.
Neither of the prompts asked for prerequisite courses, but a solid foundation in math and reading is a must.
I assume that I could have structured Prompt 3 so that I asked it to incorporate the curriculum proposed in its response to the curriculum proposed in its Prompt 2 response. If it can’t do that, I’m sure someone out there has built an app to do that.
Next Steps
If my intent were to build an AI curriculum, I would probably abandon ChatGPT 4 at this point and begin searching for relevant degrees and courses offered at colleges that I respected.
I would grade the responses to my prompts a C+ or B-. I will assume responsibility for not constructing the perfect prompts or tweaking my prompts until I have received better responses. The responses were helpful in providing me with some ideas that I could follow up with later.
The technology will get better. But I don’t know that it will ever provide more in-depth first responses to prompts that would meet the A/A+ paper requirements or the “damn good” memo to the SVP or CEO requirements. At the same time, most of my best papers and best memos were written and edited over time, not in 15 seconds.
Exercises like this lead me to believe that employees with a college degree will fare better in a world where AI tools aid most business activities. Generally, leaders don’t get to the top with mediocre performance. Using ChatGPT as your singular source of research is not going to get you a promotion.
We learn in many ways, not just from books and classes. I believe AI will enable people to do their jobs better and faster. The best performers will have an education that enables them to question the accuracy and depth of the AI responses. I value learning how to think critically more than the selection of a specific program major.
