---
title: "Reconstructed Slides: Why (Senior) Engineers Struggle to Build AI Agents — Philipp Schmid, Google DeepMind"
category: "slides"
video_id: "3_gYbhABcAE"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Why (Senior) Engineers Struggle to Build AI Agents — Philipp Schmid, Google DeepMind

## Source Video
[Why (Senior) Engineers Struggle to Build AI Agents — Philipp Schmid, Google DeepMind](https://www.youtube.com/watch?v=3_gYbhABcAE)

## Method
This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck.

## Reconstructed Slides
![[assets/reconstructed-slides/3_gYbhABcAE/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.81`
![[assets/reconstructed-slides/3_gYbhABcAE/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.36`
![[assets/reconstructed-slides/3_gYbhABcAE/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.89`
![[assets/reconstructed-slides/3_gYbhABcAE/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.4`
![[assets/reconstructed-slides/3_gYbhABcAE/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.21`
## Dense Scene-Detected Slide Candidates
- [[youtube-3_gYbhABcAE-dense-slides]]