Build Visual AI Agents With NVIDIA Nemotron 3.5 Super VL

Learn how NVIDIA Nemotron 3.5 Super VL investigates why an AI bill rose 30% using a dashboard screenshot and a scanned pricing sheet. In this walkthrough, Chris Alexiuk introduces the open 120-billion-parameter mixture-of-experts model with 12 billion active parameters, then Chia-Chih Chen demonstrates a visual investigation agent. The agent reads the dashboard, identifies a surge in thinking-token use, writes Python to compare routing options and prepares a proposal for human approval. The recommended plan stays within the team’s quality bar while projecting about $100,000 in monthly savings. NVIDIA Nemotron 3.5 Super VL combines multimodal reasoning, tool use and code generation for agents that work across text, images, charts, documents and video. It can also run on a single NVIDIA DGX Spark. Use the links and chapters below to explore the model, technical blog and developer resources. ➡️ Learn more: https://blogs.nvidia.com/blog/nemotron-3-5-super-vl/ 📝 Technical blog: https://developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning/ 📥 Download the model: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 🚀 Try on NVIDIA Build: https://build.nvidia.com/nvidia/nemotron-3.5-super-vl-120b-a12b 📚 Super VL cookbook: https://github.com/NVIDIA-NeMo/Nemotron/tree/main/usage-cookbook/Nemotron-3.5-Super-VL/visual-investigation-agent 📄 Technical report: https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3.5-Super-and-Lightning-Technical-Report.pdf Chapters: 00:00 – Introduction 00:07 – NVIDIA Nemotron 3.5 Super VL overview 00:31 – Vision-language capabilities 01:09 – Multimodal billing investigation demo 01:46 – Read dashboard metrics 01:54 – Parse a scanned pricing sheet 02:01 – Find the cause of the cost increase 02:09 – Optimize ticket routing with Python 02:16 – Prepare a proposal for human review 02:28 – Cookbook and developer resources