The new year may bring a host of virtual assistants and administrative staff to higher education. They will begin as assistants to humans, then over time they will evolve into autonomous AI staff members.

The winds of change in our field are rapidly converging, as we discussed in the previous edition of “Online: Trending Now.” The anticipated enrollment cliff, reductions in federal and state funding, increased inflation, and dwindling public support for tuition increases will combine to put even greater pressure on university budgets.

Meanwhile, the capabilities of generative AI are accelerating at compounding rates. I anticipate that universities will begin to reduce expenditures by automating some jobs, freeing up salaries and benefits as businesses have been doing over the past year. Routine jobs seem to be the first in line to be replaced, as Mark Sullivan writes in Fast Company: “Researchers from Harvard Business School, the German Institute for Economic Research, and Imperial College London Business School studied 1,388,711 job posts on a major (but undisclosed) global freelance work marketplace from July 2021 to July 2023, and found that demand for such automation-prone jobs had fallen 21% just eight months after the release of ChatGPT in late 2022.”

Matt Egan of CNN reports in “AI is replacing human tasks faster than you think,” “More than half (61%) of large US firms plan to use AI within the next year to automate tasks previously done by employees, according to a survey of finance chiefs released Thursday. Those tasks include everything from paying suppliers and doing invoices to financial reporting, said the survey conducted by Duke University and the Federal Reserve Banks of Atlanta and Richmond.”

As early as this past spring, Business Insider published a report, “How AI is changing the way we work.” The report suggests, “While GenAI is poised to have a significant impact across jobs and industries, fewer than half of business leaders feel that their companies are doing enough to empower employees to use it. Some workers remain resistant to using technology they fear could one day fully replace their roles. Programs that teach employees how to use GenAI to make themselves more productive and free up time to focus on more engaging tasks will be key to tackling AI anxiety.”

In one example, Martina Bretous reports in HubSpot that “Klarna’s AI Assistant Does the Job of 700 Customer Service Agents,” “After being live for a month, Klarna’s AI assistant handled a total of 2.3 million conversations via chat doing the equivalent of 700 full-time agents. It’s one thing to do the job, it’s another to do it well. According to their numbers, their assistant accomplished both. Using the AI Assistant led to a 25% drop in repeat inquiries and 9-minute drop in resolution time. What’s most impressive is that customer satisfaction scores stayed the same … The AI assistant costs $2–$3 million to develop and is expected to bring in $40 million in profits.”

Next-generation agents are in development and near release. As Bernard Marr reports in Forbes, “While previous iterations of AI focused on making predictions or generating content, we’re now witnessing the emergence of something far more sophisticated: AI agents that can independently perform complex tasks and make decisions. This third wave of AI, known as ‘agentic AI,’ represents a fundamental shift in how we think about and interact with artificial intelligence in the workplace.”

These agents can perform multiple tasks using the administrator’s computer and log-ons. The sophistication of the emerging new agentic models is advancing daily. In order to have a truly efficient and responsive agent, there is the expectation that the software will be aware of the user’s preferences and traits. Toward determining the logic skills, analysis ability, context awareness and readiness of current models to serve as assistants, I ran a simple, short test as one might do with a human agent who is drafting reports and responding to email and inquiries on your behalf. I asked three different LLMs that I have used most often for the past couple of months the question “Tell me something about myself that I may not know.” This will demonstrate the ability of the LLM to “remember” your exchanges and to apply some insight into human behavior.

Advanced Gemini responded,

ChatGPT 4o responded with what seems to be a web search of my background plus its own insights on that background: