---
title: "Reconstructed Slides: Build a Prompt Learning Loop - SallyAnn DeLucia & Fuad Ali, Arize"
category: "slides"
video_id: "SbcQYbrvAfI"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Build a Prompt Learning Loop - SallyAnn DeLucia & Fuad Ali, Arize

## Source Video
[Build a Prompt Learning Loop - SallyAnn DeLucia & Fuad Ali, Arize](https://www.youtube.com/watch?v=SbcQYbrvAfI)

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

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.8`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.82`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `163.59`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.15`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.25`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.33`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.32`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `167.73`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.94`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `164.7`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `164.4`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-012.jpg]]

- Source frame: `slide-012.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `171.92`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-013.jpg]]

- Source frame: `slide-013.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.28`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-014.jpg]]

- Source frame: `slide-014.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `170.29`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-015.jpg]]

- Source frame: `slide-015.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `168.53`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-016.jpg]]

- Source frame: `slide-016.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.27`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-017.jpg]]

- Source frame: `slide-017.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.95`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-018.jpg]]

- Source frame: `slide-018.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `168.58`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-019.jpg]]

- Source frame: `slide-019.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `165.85`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-020.jpg]]

- Source frame: `slide-020.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.56`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-021.jpg]]

- Source frame: `slide-021.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `170.2`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-022.jpg]]

- Source frame: `slide-022.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `171.76`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-023.jpg]]

- Source frame: `slide-023.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `153.12`
![[assets/reconstructed-slides/SbcQYbrvAfI/slide-024.jpg]]

- Source frame: `slide-024.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `167.1`
## Dense Scene-Detected Slide Candidates
- [[youtube-SbcQYbrvAfI-dense-slides]]