Reconstructed Slides: Why Agent Engineering — swyx

Source Video

Why Agent Engineering — swyx

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

• Source frame: slide-001.jpg
• Crop: contour [0, 0, 960, 540] score 175.78

• Source frame: slide-002.jpg
• Crop: full [0, 0, 960, 540] score 166.49

• Source frame: slide-003.jpg
• Crop: full [0, 0, 960, 540] score 176.79

• Source frame: slide-004.jpg
• Crop: full [0, 0, 960, 540] score 155.53

• Source frame: slide-005.jpg
• Crop: full [0, 0, 960, 540] score 166.4

• Source frame: slide-006.jpg
• Crop: contour [0, 0, 960, 540] score 175.35

• Source frame: slide-007.jpg
• Crop: contour [0, 0, 960, 540] score 175.61

• Source frame: slide-008.jpg
• Crop: full [0, 0, 960, 540] score 163.26

• Source frame: slide-009.jpg
• Crop: full [0, 0, 960, 540] score 177.27

• Source frame: slide-010.jpg
• Crop: full [0, 0, 960, 540] score 156.63

• Source frame: slide-011.jpg
• Crop: full [0, 0, 960, 540] score 175.08

• Source frame: slide-012.jpg
• Crop: full [0, 0, 960, 540] score 160.42

• Source frame: slide-013.jpg
• Crop: contour [0, 0, 960, 540] score 175.23

• Source frame: slide-014.jpg
• Crop: full [0, 0, 960, 540] score 165.8

• Source frame: slide-015.jpg
• Crop: full [0, 0, 960, 540] score 166.41

• Source frame: slide-016.jpg
• Crop: full [0, 0, 960, 540] score 176.88

• Source frame: slide-017.jpg
• Crop: full [0, 0, 960, 540] score 172.87

• Source frame: slide-018.jpg
• Crop: full [0, 0, 960, 540] score 174.45

Dense Scene-Detected Slide Candidates

• youtube 5N33E9tC400 dense slides