---
title: "Reconstructed Slides: Automating Large Scale Refactors with Parallel Agents - Robert Brennan, OpenHands"
category: "slides"
video_id: "rcsliSIy_YU"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Automating Large Scale Refactors with Parallel Agents - Robert Brennan, OpenHands

## Source Video
[Automating Large Scale Refactors with Parallel Agents - Robert Brennan, OpenHands](https://www.youtube.com/watch?v=rcsliSIy_YU)

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

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.86`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.67`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.29`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.18`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.91`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.61`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.85`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.04`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.76`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `167.29`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.12`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-012.jpg]]

- Source frame: `slide-012.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.51`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-013.jpg]]

- Source frame: `slide-013.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `153.23`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-014.jpg]]

- Source frame: `slide-014.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `154.64`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-015.jpg]]

- Source frame: `slide-015.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `156.1`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-016.jpg]]

- Source frame: `slide-016.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `155.88`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-017.jpg]]

- Source frame: `slide-017.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `156.9`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-018.jpg]]

- Source frame: `slide-018.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.13`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-019.jpg]]

- Source frame: `slide-019.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `155.29`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-020.jpg]]

- Source frame: `slide-021.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `156.27`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-021.jpg]]

- Source frame: `slide-022.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.75`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-022.jpg]]

- Source frame: `slide-023.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.27`
![[assets/reconstructed-slides/rcsliSIy_YU/slide-023.jpg]]

- Source frame: `slide-024.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `154.42`
## Dense Scene-Detected Slide Candidates
- [[youtube-rcsliSIy_YU-dense-slides]]