NVIDIA Shows Building Visual AI Agents From a Prompt With Cosmos, VSS 3.3 and Adaptive EVS
NVIDIA Developer · youtube · 2026-09-18
NVIDIA's live session demonstrates building a visual AI agent from a natural-language prompt using Cosmos and VSS 3.3:
- Workflow: combine a coding agent with VSS skills for alert verification, video search, summarization, and reporting; then review the deployment, reuse shared services, and add capabilities to a running application.
- Cost optimization: Adaptive Efficient Video Sampling (EVS) cuts processing costs on hours of footage, with live measurement of its impact on token usage, throughput, and latency.
Useful for developers building low-cost, real-time video analysis on long streams.
More from coding & agent
- Butterfly traces multi-agent failures with graphs, 62.5% accuracy vs 53.8% for log prompting — JeremyCMorgan · 2026-11-04
- Free course covers the 4 hard problems of production generative media agents — Al_Grigor · 2026-11-04
- Quota reset night: Codex back to 100% while Claude shows just 10% left — rudrank · 2026-11-04
- Self-improving software is inevitable: closing the agent-observability loop — bibryam · 2026-11-04
- Building a 7-GPU 132GB VRAM local inference rig: consolidate on EPYC or split across two systems? — infectiousstupidity · 2026-11-04
- Founder of 50-person, 12-country team says he talks to AI agents more than humans — Scobleizer · 2026-11-04