---
title: "Reconstructed Slides: How to build world-class AI products — Sarah Sachs (AI lead @ Notion) &  Carlos Esteban (Braintrust)"
category: "slides"
video_id: "6YdPI9YbjbI"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: How to build world-class AI products — Sarah Sachs (AI lead @ Notion) &  Carlos Esteban (Braintrust)

## Source Video
[How to build world-class AI products — Sarah Sachs (AI lead @ Notion) &  Carlos Esteban (Braintrust)](https://www.youtube.com/watch?v=6YdPI9YbjbI)

## 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/6YdPI9YbjbI/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.15`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.75`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.87`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `161.72`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.23`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.99`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `159.12`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `159.21`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.21`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `162.16`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.57`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-012.jpg]]

- Source frame: `slide-012.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `155.41`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-013.jpg]]

- Source frame: `slide-013.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `158.4`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-014.jpg]]

- Source frame: `slide-014.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.67`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-015.jpg]]

- Source frame: `slide-015.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.87`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-016.jpg]]

- Source frame: `slide-016.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.19`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-017.jpg]]

- Source frame: `slide-017.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `161.63`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-018.jpg]]

- Source frame: `slide-018.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.23`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-019.jpg]]

- Source frame: `slide-019.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `161.44`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-020.jpg]]

- Source frame: `slide-020.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.44`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-021.jpg]]

- Source frame: `slide-022.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `158.56`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-022.jpg]]

- Source frame: `slide-023.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.24`
![[assets/reconstructed-slides/6YdPI9YbjbI/slide-023.jpg]]

- Source frame: `slide-024.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.18`
## Dense Scene-Detected Slide Candidates
- [[youtube-6YdPI9YbjbI-dense-slides]]