With AI agents, will IT pros be able to find entry-level roles?

Many companies are claiming we’re in an “agentic moment,” with AI agents boosting employee efficiency. But will this technology also put entry-level IT positions at risk?

Visier Chief Evangelist and Chief Customer Officer, or chief customer and chief people officer, per LinkedIn, Paul Rubenstein told IT Brew that AI agents could redefine what it means to manage an enterprise, specifically in terms of adding an agent at the “last mile of corporate performance.”

“The ability to go straight to the raw data very quickly and for most senior managers to interrogate or set up patterns that they want to detect and listen for, AI’s just great at that, and changes what we would use middle management for,” Rubenstein said.

But AI agents could also impact those IT professionals who work for middle management on those corporate front lines, monitoring systems and maintaining infrastructure. Almost half (45%) of workers reported that they foresee AI agents replacing IT positions, according to research from Kong.

Rearranging the stack. Emanuel Salmona, the co-founder and CEO of Nagoma Security, described an organization’s structure like a pyramid, with AI agents having their biggest impact at the base of it.

Putting AI agents at the “base” of a company’s structure can make sense from a risk and implementation standpoint. Salmona said that many of the initial functions being taken on by agents include those currently covered by early career professionals.

Given how AI agents could be a black box, making multiple decisions without human oversight, making workflows as transparent as possible will be critical, Salmona added.

“There are going to be changes in the organization, there’s going to be a lot more need for monitoring and putting guardrails into place,” Salmona said. “Ultimately, there’s going to be the need of working much better in terms of cross-functional rules, because we can’t just put an AI agent and let them work in their own silo.”

Organizations are also under pressure to make those decisions around guardrails and transparency quickly. Kong’s report found that 90% of respondents said their companies are “actively adopting AI agents.” The big question is whether that will translate into job loss.

The big question. If AI models are replacing more junior IT positions, while organizations upskill mid-career software engineers and developers to fill more senior positions, are those IT pros looking for entry-level positions in danger of not finding work?

Jason McGhee, the co-founder and CTO at software development company Writ, said that he doesn’t quite believe the IT industry is capable of making an entire generation of people unemployable. He believes that people interested in future-proofing their careers should focus instead on developing more advanced capabilities and knowledge.

“We might see a shift,” McGhee said. “People tend to require the types of skills that tend to [come] later, like system design and architecture and being able to review code.” Soft skills and coaching are also skills that transfer well, he noted.

Research backs up that idea: Gartner reported that by 2027, 80% of software engineers will need to upskill in response to generative AI.

With the industry-wide emphasis on upskilling and training to narrow the AI knowledge gap, it’s understood that not every position requires the same amount of AI application.

Some IT roles may prove more “AI proof” than others. Salmona said that in cybersecurity specifically, there’s still a lot of manual work that requires a human. In a typical cybersecurity workflow, for example, a worker will need to figure out what something means in context, learn its status, and take one of several possible actions.

In a best case scenario, organizations that replaced some IT positions with IT agents could be giving those remaining IT pros more time to apply creativity to higher-level tasks.

“This is a good thing, because it means that people can focus on things that really only people can do,” Salmona said. “If the agent can do it, well, that’s a good signal that we need to elevate ourselves.”