I Used an AI Agent to Make a Product Video. The Cost Was $0, But There's a Catch.

Can an AI Agent Make a Professional Explainer Video for Pocket Change?

The promise of projects like OpenMontage, an open-source agentic video production system, is seductive: describe a video in plain English, and an AI agent handles the rest. Research, scripting, asset generation, editing, rendering—the full stack. To put this to a real-world test, I tasked an agent with producing a 75-second explainer video on a non-trivial topic: local-first software. The goal was a hybrid of animated diagrams, abstract b-roll, and clean text overlays—a classic tech explainer. The question was simple: could the agent deliver a professional product, and what would it really cost?

The Plan: Smooth Sailing and a Reference Point

Getting started with OpenMontage was a breeze. Aside from installing FFmpeg, a well-documented prerequisite, the make setup command handled all Python and Node dependencies cleanly. The journey began not with a blank prompt, but with a reference video I chose for its polish and recency: Linear's "Introducing Linear Agent." OpenMontage's video analyzer ingested the YouTube URL and returned something far more insightful than a mere transcript. It produced a five-aspect cinematographic breakdown—subject, motion, scene, framing, camera—and even inferred why the style worked, noting the "high-contrast dark palette... to make plain text look incredibly premium."