IT Is Becoming an HR Department for AI Agents
Techstrong TV Interviews
•
18m
NVIDIA CEO Jensen Huang once said the IT department will become the HR department for AI agents. Alan Shimel talks with John Capobianco, head of AI and developer relations at Itential, about what managing AI agents looks like in practice for network and infrastructure teams.
From the factory floor to network automation
Capobianco started out working 12-hour shifts in an aluminum factory while he studied computer programming. Later, he ran the network at Empire Life and then spent a decade as senior network architect for the Canadian Parliament. There, scale and complexity pushed his team into network automation with Python around 2016. After that, he spent three years at Cisco, worked at Selector AI and joined Itential this year.
Governed AI agents with Itential
Itential has led infrastructure automation and orchestration for years, and it was early to adopt the Model Context Protocol. Now, engineers can describe an agent in plain network terms and build it with builder skills. What sets the platform apart is governance: role-based access control, audit and authentication. At the Lumen Innovation Summit, for example, about 35 engineers built roughly 50 agents in a 45-minute workshop.
Managing AI agents like a team
Capobianco now spends his time managing AI agents rather than devices. An orchestrator agent runs a frontier model and hands work to other agents, each with the right model for the job. A planning agent writes the change plan, and a decision-making model scores it. Then a configuration agent with tightly scoped tools pushes the change, while a low-cost open-weight model handles emails and Slack updates. As a result, he picks models and tools much like a manager picks staff.
Why decision-making models matter
Not every task needs a large general-purpose model. Smaller, specialized decision-making models can evaluate evidence, validate proposed actions and check results before an agent moves on. That leads to more reliable decisions and stronger guardrails as teams give agents more autonomy.
Managing AI agents is quickly becoming a core IT skill. Explore more DevOps and automation videos and the latest Techstrong TV interviews.
For more information please visit itential.com
Up Next in Techstrong TV Interviews
-
What's The One Piece Of Infra You'd N...
Where should organizations draw the line when giving AI control over critical infrastructure? Security leaders discuss why identity and access management, privileged credentials, key management and recovery systems require human oversight. Explore the risks of autonomous AI, the importance of pro...
-
AI Agents Aren't Rogue. They're Relen...
Doing Exactly What They're Told
AI agents are often described as going rogue. In reality, most are doing exactly what they were asked to do. They just pursue the goal more creatively than people would, and they never get tired.Bitdefender Director of Cybersecurity Services Nick Jackson examines...
-
The Sticker Shock of AI Infrastructur...
Governance Meets the AI Era
AI infrastructure costs are about to climb, and many organizations don't see it coming. AI agents will consume far more resources than today's workloads. Most teams only notice when the first bill arrives.CloudBolt CEO Alexander Thomson examines that challenge with M...