---
title: "Dense Slides: WF2026: Autoresearch & Keynotes ft. Anthropic, Google DeepMind, Amazon AGI, Sonar, Arena, Recursive"
category: "slides"
video_id: "4sX_He5c4sI"
sourceLabels: ["Captured video frames", "Local OpenCV slide-region detection"]
---

# Dense Slides: WF2026: Autoresearch & Keynotes ft. Anthropic, Google DeepMind, Amazon AGI, Sonar, Arena, Recursive

## Source Video
[WF2026: Autoresearch & Keynotes ft. Anthropic, Google DeepMind, Amazon AGI, Sonar, Arena, Recursive](https://www.youtube.com/watch?v=4sX_He5c4sI)

## Method
This deck is slide-only. The existing captured video frame set supplies candidate frames, then local OpenCV rejects sponsor/title/speaker-only frames, crops visible slide surfaces, deduplicates, and saves the cropped slide images.

## Cropped Visible Slides
![[assets/dense-slides/4sX_He5c4sI/slide-001.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-001.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: agent_vision.

Slide text:

> CAPABILITY OVERHANG
> Claude gets smarter in spiky ways

![[assets/dense-slides/4sX_He5c4sI/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> System Prompt Design
> Small system prompt, few tools, lots of examples
> Large system prompt, lots of examples, many tools
> Smaller system prompt, tool search, no examples

![[assets/dense-slides/4sX_He5c4sI/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.

Slide text:

> Agenda
> 1. Meet OG Assist
> 2. The Origin Story
> 3. Betting on Effect
> 4. The Core Agent Loop
> 5. A2A, Evals & Sandboxing
> 6. Long Context Handling
> 7. Monitoring & Observability
> 8. Tools, Skills & Dev Workflows

![[assets/dense-slides/4sX_He5c4sI/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: agent_vision.

Slide text:

> Origin Story
> One bet on agents, one immediate yes.

![[assets/dense-slides/4sX_He5c4sI/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-005.html)
- AI slide classifier: `content_slide` confidence `0.94`
- Text source: agent_vision.
- OCR decision: ready — Code and small explanatory text are better handled by OCR than manual transcription.

Slide text:

> Our agent loop, rebuilt Effect-native.

![[assets/dense-slides/4sX_He5c4sI/slide-006.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-006.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: agent_vision.
- OCR decision: ready — Dense diagram labels and small body text make OCR preferable.

Slide text:

> Production Evals for Agentic Systems

![[assets/dense-slides/4sX_He5c4sI/slide-007.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-007.html)
- AI slide classifier: `content_slide` confidence `0.91`
- Text source: none.
- OCR decision: ready — Cropped headline plus many small chart labels are OCR-suitable.
- Slide text: not surfaced (`illegible` by AI classifier).
![[assets/dense-slides/4sX_He5c4sI/slide-008.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-008.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: agent_vision.
- OCR decision: ready — Dense diagram slide with small subtitle/body text is OCR-suitable.

Slide text:

> Production Evals for Agentic Systems

![[assets/dense-slides/4sX_He5c4sI/slide-009.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-009.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.
- OCR decision: ready — Diagram slide with multiple small labels and a central illustration; OCR will capture labels more reliably than manual reading.

Slide text:

> The Anatomy Of Agentic Failure

![[assets/dense-slides/4sX_He5c4sI/slide-010.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-010.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: none.
- OCR decision: ready — Dense diagram with several small callout boxes and circular annotations; OCR is the right capture method.
![[assets/dense-slides/4sX_He5c4sI/slide-011.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-011.html)
- AI slide classifier: `content_slide` confidence `0.76`
- Text source: agent_vision.
- OCR decision: ready — Large embedded product UI screenshot with many small labels and UI chrome; OCR will be more reliable than hand transcription.

Slide text:

> Engineering the future of AI

![[assets/dense-slides/4sX_He5c4sI/slide-012.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-012.html)
- AI slide classifier: `content_slide` confidence `0.84`
- Text source: none.
- OCR decision: ready — Product UI screenshot dominates the frame and contains many small interface labels; OCR is suitable.
![[assets/dense-slides/4sX_He5c4sI/slide-013.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-013.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.

Slide text:

> Principle 5 Modularity
> Which capabilities should be reusable, and which stay local?

![[assets/dense-slides/4sX_He5c4sI/slide-014.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/4sX_He5c4sI/slide-014.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: agent_vision.

Slide text:

> The agent is its data
> Specifically: the log


Classification audit: `raw/sources/slide-ai-classification/dense/4sX_He5c4sI/audit.json`