---
title: "Reconstructed Slides: OpenAI + @Temporalio : Building Durable, Production Ready Agents - Cornelia Davis, Temporal"
category: "slides"
video_id: "k8cnVCMYmNc"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: OpenAI + @Temporalio : Building Durable, Production Ready Agents - Cornelia Davis, Temporal

## Source Video
[OpenAI + @Temporalio : Building Durable, Production Ready Agents - Cornelia Davis, Temporal](https://www.youtube.com/watch?v=k8cnVCMYmNc)

## 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/k8cnVCMYmNc/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.49`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.11`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.59`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `156.81`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.02`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.4`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `158.77`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.24`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `165.34`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.5`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.56`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-012.jpg]]

- Source frame: `slide-012.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.0`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-013.jpg]]

- Source frame: `slide-013.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.01`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-014.jpg]]

- Source frame: `slide-014.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.25`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-015.jpg]]

- Source frame: `slide-015.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.65`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-016.jpg]]

- Source frame: `slide-016.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `178.11`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-017.jpg]]

- Source frame: `slide-017.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.22`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-018.jpg]]

- Source frame: `slide-019.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `167.98`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-019.jpg]]

- Source frame: `slide-020.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.11`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-020.jpg]]

- Source frame: `slide-021.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.6`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-021.jpg]]

- Source frame: `slide-022.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.99`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-022.jpg]]

- Source frame: `slide-023.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `164.2`
![[assets/reconstructed-slides/k8cnVCMYmNc/slide-023.jpg]]

- Source frame: `slide-024.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `178.1`
## Dense Scene-Detected Slide Candidates
- [[youtube-k8cnVCMYmNc-dense-slides]]