---
title: "Reconstructed Slides: Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex"
category: "slides"
video_id: "jVGCulhBRZI"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex

## Source Video
[Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex](https://www.youtube.com/watch?v=jVGCulhBRZI)

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

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.13`
![[assets/reconstructed-slides/jVGCulhBRZI/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.6`
![[assets/reconstructed-slides/jVGCulhBRZI/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.32`
![[assets/reconstructed-slides/jVGCulhBRZI/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.6`
![[assets/reconstructed-slides/jVGCulhBRZI/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.15`
![[assets/reconstructed-slides/jVGCulhBRZI/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `158.37`
![[assets/reconstructed-slides/jVGCulhBRZI/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.75`
![[assets/reconstructed-slides/jVGCulhBRZI/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `158.81`
## Dense Scene-Detected Slide Candidates
- [[youtube-jVGCulhBRZI-dense-slides]]