Google Unveils Agentic Video Understanding Feature in Gemini AI Models

Google has released a new feature called agentic video understanding, which is now available in its Gemini AI models. This feature allows for more efficient and accurate processing of long-form videos by enabling the model to dynamically search, scan, and inspect target video segments across visual frames, audio, and transcripts.

The agentic video understanding feature reduces token consumption by up to 88% and analysis costs by up to 66%, while boosting accuracy by up to 7%. This is particularly beneficial for long-form videos, such as multi-hour recordings or 90-minute lectures, where static processing can be costly and inaccurate.

Agentic video understanding enables Gemini to take an active role in determining what to watch, at what speed, and through which modality (frames, audio, or transcript), significantly reducing development overheads. This feature is available via the Gemini API in Google AI Studio and Gemini Enterprise Agent Platform, launching across Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite.