---
title: "Reconstructed Slides: Making Codebases Agent Ready – Eno Reyes, Factory AI"
category: "slides"
video_id: "ShuJ_CN6zr4"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Making Codebases Agent Ready – Eno Reyes, Factory AI

## Source Video
[Making Codebases Agent Ready – Eno Reyes, Factory AI](https://www.youtube.com/watch?v=ShuJ_CN6zr4)

## 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/ShuJ_CN6zr4/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.24`
![[assets/reconstructed-slides/ShuJ_CN6zr4/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.56`
![[assets/reconstructed-slides/ShuJ_CN6zr4/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.22`
![[assets/reconstructed-slides/ShuJ_CN6zr4/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.59`
![[assets/reconstructed-slides/ShuJ_CN6zr4/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `165.9`
![[assets/reconstructed-slides/ShuJ_CN6zr4/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `171.25`
![[assets/reconstructed-slides/ShuJ_CN6zr4/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `159.39`
## Dense Scene-Detected Slide Candidates
- [[youtube-ShuJ_CN6zr4-dense-slides]]