---
title: "Reconstructed Slides: Building Intelligent Research Agents with Manus - Ivan Leo, Manus AI (now Meta Superintelligence)"
category: "slides"
video_id: "xz0-brt56L8"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Building Intelligent Research Agents with Manus - Ivan Leo, Manus AI (now Meta Superintelligence)

## Source Video
[Building Intelligent Research Agents with Manus - Ivan Leo, Manus AI (now Meta Superintelligence)](https://www.youtube.com/watch?v=xz0-brt56L8)

## 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/xz0-brt56L8/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `170.06`
![[assets/reconstructed-slides/xz0-brt56L8/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.14`
![[assets/reconstructed-slides/xz0-brt56L8/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `172.15`
![[assets/reconstructed-slides/xz0-brt56L8/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.42`
![[assets/reconstructed-slides/xz0-brt56L8/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.28`
![[assets/reconstructed-slides/xz0-brt56L8/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `165.32`
![[assets/reconstructed-slides/xz0-brt56L8/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `156.05`
![[assets/reconstructed-slides/xz0-brt56L8/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `174.9`
![[assets/reconstructed-slides/xz0-brt56L8/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.99`
![[assets/reconstructed-slides/xz0-brt56L8/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `169.56`
![[assets/reconstructed-slides/xz0-brt56L8/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `170.46`
![[assets/reconstructed-slides/xz0-brt56L8/slide-012.jpg]]

- Source frame: `slide-012.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `170.32`
![[assets/reconstructed-slides/xz0-brt56L8/slide-013.jpg]]

- Source frame: `slide-013.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.09`
![[assets/reconstructed-slides/xz0-brt56L8/slide-014.jpg]]

- Source frame: `slide-014.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.82`
![[assets/reconstructed-slides/xz0-brt56L8/slide-015.jpg]]

- Source frame: `slide-015.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `154.91`
![[assets/reconstructed-slides/xz0-brt56L8/slide-016.jpg]]

- Source frame: `slide-016.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `154.89`
![[assets/reconstructed-slides/xz0-brt56L8/slide-017.jpg]]

- Source frame: `slide-018.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.16`
![[assets/reconstructed-slides/xz0-brt56L8/slide-018.jpg]]

- Source frame: `slide-019.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `153.11`
![[assets/reconstructed-slides/xz0-brt56L8/slide-019.jpg]]

- Source frame: `slide-020.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `153.72`
![[assets/reconstructed-slides/xz0-brt56L8/slide-020.jpg]]

- Source frame: `slide-021.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `169.76`
![[assets/reconstructed-slides/xz0-brt56L8/slide-021.jpg]]

- Source frame: `slide-022.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `158.43`
![[assets/reconstructed-slides/xz0-brt56L8/slide-022.jpg]]

- Source frame: `slide-023.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.65`
![[assets/reconstructed-slides/xz0-brt56L8/slide-023.jpg]]

- Source frame: `slide-024.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.65`
## Dense Scene-Detected Slide Candidates
- [[youtube-xz0-brt56L8-dense-slides]]