---
title: "Reconstructed Slides: Letting AI Interface with your App with MCP — Kent C Dodds"
category: "slides"
video_id: "EyZiAp0pelw"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Letting AI Interface with your App with MCP — Kent C Dodds

## Source Video
[Letting AI Interface with your App with MCP — Kent C Dodds](https://www.youtube.com/watch?v=EyZiAp0pelw)

## 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/EyZiAp0pelw/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `172.63`
![[assets/reconstructed-slides/EyZiAp0pelw/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.67`
![[assets/reconstructed-slides/EyZiAp0pelw/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.0`
![[assets/reconstructed-slides/EyZiAp0pelw/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `159.53`
![[assets/reconstructed-slides/EyZiAp0pelw/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `167.09`
![[assets/reconstructed-slides/EyZiAp0pelw/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `162.69`
![[assets/reconstructed-slides/EyZiAp0pelw/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `159.93`
![[assets/reconstructed-slides/EyZiAp0pelw/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.29`
## Dense Scene-Detected Slide Candidates
- [[youtube-EyZiAp0pelw-dense-slides]]