How the Developer Community Builds Sub-Agents with NVIDIA Nemotron 3 Nano Omni | Nemotron Labs

NVIDIA Nemotron 3 Nano Omni is here — a multimodal open model built to process and reason across text, images, and more, purpose-built for autonomous and coordinated agent systems. In this session, we bring in voices from the AI community — Corey Noles (The Neuron) and Wendell Wilson (Level1Techs) — to dig into what Nemotron 3 Nano Omni actually looks like in practice, including a live demo. We'll tackle the questions that matter most right now: which model do you reach for and when? How do you architect sub-agents that work together effectively? And where does a multimodal model like Nemotron 3 Nano Omni unlock capabilities that text-only models simply can't? What you'll learn: - How Nemotron 3 Nano Omni's multimodal capabilities open new possibilities for agent perception and reasoning - When and how to use sub-agents — and how to coordinate models within a multi-agent system - How to choose the right model for specific agent tasks - What the Nemotron Coalition approach means for open model development and customization Have questions about sub-agents or model selection? Drop them live — our guests will answer them in real time.