TechPrufer
Get started
DeepMind
DeepMind logoDeepMind · Feature trail

Agentic Video Understanding

1 post · Sep 2026

What this trail covers

Agentic video understanding is introduced, enhancing Gemini models (3.7 Flash, 3.6 Flash, 3.5 Flash-Lite) with native video tools for dynamic analysis. This approach reduces costs and token usage while improving accuracy for video processing tasks like sub-second moment retrieval, anomaly detection, and precise counting. It is available via the Gemini API and will be integrated into Google products like the Gemini app and YouTube's 'Ask YouTube' feature.

All DeepMind trails
  1. Introducing agentic video understanding with GeminiThis post introduces agentic video understanding across Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite models. It details how the system dynamically searches and inspects video segments using native video tools, reducing analysis costs by up to 66% and token consumption by up to 88%, while improving accuracy by up to 7%. The core mechanism involves an agentic loop that invokes internal tools to load relevant video parts, enabling capabilities like sub-second moment retrieval, long-form search, anomaly detection, and action/object counting. The feature is available via the Gemini API and will be integrated into the Gemini app and YouTube's 'Ask YouTube' feature.