---
title: "B-Rolls Finder: Search YouTube by Conversation"
description: "B-Rolls Finder searches YouTube through a chat interface to surface the right b-roll fast. Here is how I made finding video footage feel like a conversation."
type: "build"
locale: "en"
category: "tool"
canonical: "https://agenticschool.dev/builds/b-rolls-finder"
dateModified: "2026-06-12"
---

# B-Rolls Finder: Search YouTube by Conversation

- Category: tool
- Status: internal
- Stack: YouTube Data API, Node.js, React, LLM, TypeScript
- Updated: 2026-06-12
- Keywords: YouTube API, b-roll, chat interface, video search, rate limits
- Canonical URL: https://agenticschool.dev/builds/b-rolls-finder
- Locale: en

> Finding the right clip by talking to a chat box, not scrubbing timelines.

B-Rolls Finder searches YouTube through a chat interface to surface the right b-roll fast. Here is how I made finding video footage feel like a conversation.

## The problem with finding footage

When you are editing a video, finding the right b-roll clip is a slog: you type keywords into YouTube, scrub through results, refine, and repeat. B-Rolls Finder was my attempt to replace that with a conversation. You describe the mood and content you want, and it goes and finds candidates.

## Chat as the interface, the API as the engine

Under the hood it is the YouTube Data API doing the searching, but the interface is a chat box. The LLM turns a loose human request like "calm aerial shots of a city at dawn" into precise queries, runs them, and presents the results conversationally so you can refine in plain language.

- You describe what you want in words; the model turns that into real search queries.
- Results come back as a short, scannable shortlist instead of an endless scroll.
- You refine by replying, the same way you would tell a human assistant "more like the second one".

## The lesson about good interfaces

The API was the easy part; the win was the interface. The same data, the same YouTube search, felt completely different when wrapped in a conversation instead of a search box. It reminded me that a lot of the value in AI products right now is not new capability, it is a better interface to capability that already exists. I also ran into the practical realities of working with a third-party API: quotas, rate limits and the need to cache, all of which I had read about in the abstract and only really understood once they bit me. Respecting someone else API is part of being a good citizen and part of not getting cut off.

## Lessons learned

- A conversational interface can transform a tool without changing the underlying data at all.
- A lot of AI product value is a better interface to existing capability, not brand new capability.
- Third-party APIs have quotas and rate limits. Cache results and respect them or you get cut off.
- Let the model translate loose human intent into precise queries. That translation is the real feature.