---
title: "Slides: AI Engineer World's Fair: Building Reelful - Agentic Video Editor"
category: "slides"
video_id: "AheG9p_JXVw"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata", "AI slide classification"]
---

# Slides: AI Engineer World's Fair: Building Reelful - Agentic Video Editor

## Source Video
[AI Engineer World's Fair: Building Reelful - Agentic Video Editor](https://www.youtube.com/watch?v=AheG9p_JXVw)

## Relationship To World's Fair 2026
These slides are extracted from a public YouTube video connected to World's Fair 2026. Speaker-matched clips outside the official AI Engineer channel are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

## Related Scheduled Sessions
- [[2026-07-01-ekaterina-deyneka-building-an-agentic-video-editor-for-mass-consumer|Building an Agentic Video Editor for Mass Consumer]] — Ekaterina Deyneka, Reelful; Day 4, 11:40am-12:00pm, Track 1, Generative Media.

## Extracted Slides
No slide-like frames are visible after AI slide classification. Rejected frames remain stored as evidence and are listed below.

### Hidden Non-Slide Evidence
- [`slide-001.jpg`](/assets/slides/AheG9p_JXVw/slide-001.jpg) — `speaker_stage` confidence `0.97`; Stage photo with presenter and projected slide screens; not a clean readable slide frame.
- [`slide-002.jpg`](/assets/slides/AheG9p_JXVw/slide-002.jpg) — `speaker_stage` confidence `0.97`; Stage photo with presenter and projected promo images; not a readable presentation slide.
- [`slide-003.jpg`](/assets/slides/AheG9p_JXVw/slide-003.jpg) — `speaker_stage` confidence `0.98`; Stage photo with presenter and projected QR/promo screen; not a clean slide frame.
- [`slide-004.jpg`](/assets/slides/AheG9p_JXVw/slide-004.jpg) — `speaker_stage` confidence `0.99`; Stage photo with presenter and mostly blank/dark projection; not a readable slide.

Classification audit: `raw/sources/slide-ai-classification/slides/AheG9p_JXVw/audit.json`

## Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.