---
title: "Reconstructed Slides: Katelyn Lesse – Evolving Claude APIs for Agents, Anthropic"
category: "slides"
video_id: "aqW68Is_Kj4"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Katelyn Lesse – Evolving Claude APIs for Agents, Anthropic

## Source Video
[Katelyn Lesse – Evolving Claude APIs for Agents, Anthropic](https://www.youtube.com/watch?v=aqW68Is_Kj4)

## 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/aqW68Is_Kj4/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `169.88`
![[assets/reconstructed-slides/aqW68Is_Kj4/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `168.57`
![[assets/reconstructed-slides/aqW68Is_Kj4/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.87`
![[assets/reconstructed-slides/aqW68Is_Kj4/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `175.51`
![[assets/reconstructed-slides/aqW68Is_Kj4/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.77`
![[assets/reconstructed-slides/aqW68Is_Kj4/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `175.54`
![[assets/reconstructed-slides/aqW68Is_Kj4/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.61`
![[assets/reconstructed-slides/aqW68Is_Kj4/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.09`
![[assets/reconstructed-slides/aqW68Is_Kj4/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.62`
![[assets/reconstructed-slides/aqW68Is_Kj4/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.26`
![[assets/reconstructed-slides/aqW68Is_Kj4/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.29`
## Dense Scene-Detected Slide Candidates
- [[youtube-aqW68Is_Kj4-dense-slides]]