# Agentic approaches to processing long videos with Gemini

## Executive summary

Agentic video understanding with Gemini allows developers to process long-form videos without submitting the entire content, which could exceed 100,000 tokens. Instead, the model uses an agentic loop (thinking, acting, observing) and specialized tools—such as `get transcript`, `get frames`, and audio extraction—to iteratively zoom in on relevant information, significantly reducing token usage and improving processing performance.

## Key takeaways

- Token Efficiency: By using an agentic approach, the model avoids submitting the entire video content (which can exceed 100,000 tokens), leading to massive token reductions and lower latency.
- Agentic Workflow: The process involves the model first determining necessary tools (e.g., `get transcripts`, `get frames`) before executing a traditional agentic loop of thinking, acting, observing, and iterating until the answer is derived.
- Targeted Analysis: This technique improves performance by allowing the model to 'zoom in' on specific functions or segments within the video that are most relevant to the query, rather than processing all data equally.

## Technical details

- Agentic Video Processing Tools: The model can utilize specific tools for video analysis: `get transcript` (to extract text segments), `get frames` (allowing specification of desired frames and frames per second), and audio extraction.

## Practical implications

- Enables the processing of extremely long-form video data (e.g., detailed build logs or comprehensive recordings) within API constraints.
- Reduces operational costs and latency associated with massive token consumption during AI analysis pipelines.
- Allows for highly targeted querying, ensuring that computational resources are focused only on the most relevant parts of the video content.

## Topics

Video Processing, AI Agents, Gemini, Token Management, Agentic Workflow

Source: https://www.youtube.com/watch?v=HyfhaGNVKUA