Reconstructed Slides: Building a Smarter AI Agent with Neural RAG - Will Bryk, Exa.ai

Source Video

Building a Smarter AI Agent with Neural RAG - Will Bryk, Exa.ai

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: full [0, 0, 960, 540] score 160.13

• Source frame: slide-002.jpg
• Crop: full [0, 0, 960, 540] score 176.0

• Source frame: slide-003.jpg
• Crop: full [0, 0, 960, 540] score 177.57

• Source frame: slide-004.jpg
• Crop: full [0, 0, 960, 540] score 175.8

• Source frame: slide-005.jpg
• Crop: full [0, 0, 960, 540] score 176.66

• Source frame: slide-006.jpg
• Crop: full [0, 0, 960, 540] score 176.41

• Source frame: slide-007.jpg
• Crop: full [0, 0, 960, 540] score 176.45

• Source frame: slide-008.jpg
• Crop: full [0, 0, 960, 540] score 157.99

• Source frame: slide-009.jpg
• Crop: full [0, 0, 960, 540] score 176.44

• Source frame: slide-010.jpg
• Crop: full [0, 0, 960, 540] score 155.62

• Source frame: slide-011.jpg
• Crop: full [0, 0, 960, 540] score 157.96

• Source frame: slide-012.jpg
• Crop: full [0, 0, 960, 540] score 157.58

Dense Scene-Detected Slide Candidates

• youtube xnXqpUW_Kp8 dense slides